subject:(matrix factorization)

Texas A&M University

1. Belsare, Aditya Sanjay. Sparse LU Factorization for Large Circuit Matrices on Heterogenous Parallel Computing Platforms.

Degree: MS, Computer Engineering, 2014, Texas A&M University

URL: http://hdl.handle.net/1969.1/153210

► Direct sparse solvers are traditionally known to be robust, yet difficult to parallelize. In the context of circuit simulators, they present an important bottleneck where… (more)

Subjects/Keywords: Sparse matrix solver; LU Factorization

Record Details Similar Records Cite « Share

❌

APA · Chicago · MLA · Vancouver · CSE | Export to Zotero / EndNote / Reference Manager

APA (6^th Edition):

Belsare, A. S. (2014). Sparse LU Factorization for Large Circuit Matrices on Heterogenous Parallel Computing Platforms. (Masters Thesis). Texas A&M University. Retrieved from http://hdl.handle.net/1969.1/153210

Chicago Manual of Style (16^th Edition):

Belsare, Aditya Sanjay. “Sparse LU Factorization for Large Circuit Matrices on Heterogenous Parallel Computing Platforms.” 2014. Masters Thesis, Texas A&M University. Accessed April 10, 2021. http://hdl.handle.net/1969.1/153210.

MLA Handbook (7^th Edition):

Belsare, Aditya Sanjay. “Sparse LU Factorization for Large Circuit Matrices on Heterogenous Parallel Computing Platforms.” 2014. Web. 10 Apr 2021.

Vancouver:

Belsare AS. Sparse LU Factorization for Large Circuit Matrices on Heterogenous Parallel Computing Platforms. [Internet] [Masters thesis]. Texas A&M University; 2014. [cited 2021 Apr 10]. Available from: http://hdl.handle.net/1969.1/153210.

Council of Science Editors:

Belsare AS. Sparse LU Factorization for Large Circuit Matrices on Heterogenous Parallel Computing Platforms. [Masters Thesis]. Texas A&M University; 2014. Available from: http://hdl.handle.net/1969.1/153210

Penn State University

2. Li, Yunhang. Matrix Factorization Method For Lagre Recommendation System.

Degree: 2015, Penn State University

URL: https://submit-etda.libraries.psu.edu/catalog/26488

► Recommendation system is a very popular topic in recent years. It’s very efficient to utilize machine learning algorithms to improve the performance of recommendation systems.… (more)

Subjects/Keywords: Recommendation system; Matrix Factorization

Record Details Similar Records Cite « Share

❌

APA · Chicago · MLA · Vancouver · CSE | Export to Zotero / EndNote / Reference Manager

APA (6^th Edition):

Li, Y. (2015). Matrix Factorization Method For Lagre Recommendation System. (Thesis). Penn State University. Retrieved from https://submit-etda.libraries.psu.edu/catalog/26488

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

Chicago Manual of Style (16^th Edition):

Li, Yunhang. “Matrix Factorization Method For Lagre Recommendation System.” 2015. Thesis, Penn State University. Accessed April 10, 2021. https://submit-etda.libraries.psu.edu/catalog/26488.

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

MLA Handbook (7^th Edition):

Li, Yunhang. “Matrix Factorization Method For Lagre Recommendation System.” 2015. Web. 10 Apr 2021.

Vancouver:

Li Y. Matrix Factorization Method For Lagre Recommendation System. [Internet] [Thesis]. Penn State University; 2015. [cited 2021 Apr 10]. Available from: https://submit-etda.libraries.psu.edu/catalog/26488.

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

Council of Science Editors:

Li Y. Matrix Factorization Method For Lagre Recommendation System. [Thesis]. Penn State University; 2015. Available from: https://submit-etda.libraries.psu.edu/catalog/26488

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

University of New Mexico

3. Potluru, Vamsi. Matrix Factorization: Nonnegativity, Sparsity and Independence.

Degree: Department of Computer Science, 2014, University of New Mexico

URL: http://hdl.handle.net/1928/24336

► Matrix factorization arises in a wide range of application domains and is useful for extracting the latent features in the dataset. Examples include recommender systems,… (more)

Subjects/Keywords: Matrix factorization; Nonnegativity; Sparsity; Independence

Record Details Similar Records Cite « Share

❌

APA · Chicago · MLA · Vancouver · CSE | Export to Zotero / EndNote / Reference Manager

APA (6^th Edition):

Potluru, V. (2014). Matrix Factorization: Nonnegativity, Sparsity and Independence. (Doctoral Dissertation). University of New Mexico. Retrieved from http://hdl.handle.net/1928/24336

Chicago Manual of Style (16^th Edition):

Potluru, Vamsi. “Matrix Factorization: Nonnegativity, Sparsity and Independence.” 2014. Doctoral Dissertation, University of New Mexico. Accessed April 10, 2021. http://hdl.handle.net/1928/24336.

MLA Handbook (7^th Edition):

Potluru, Vamsi. “Matrix Factorization: Nonnegativity, Sparsity and Independence.” 2014. Web. 10 Apr 2021.

Vancouver:

Potluru V. Matrix Factorization: Nonnegativity, Sparsity and Independence. [Internet] [Doctoral dissertation]. University of New Mexico; 2014. [cited 2021 Apr 10]. Available from: http://hdl.handle.net/1928/24336.

Council of Science Editors:

Potluru V. Matrix Factorization: Nonnegativity, Sparsity and Independence. [Doctoral Dissertation]. University of New Mexico; 2014. Available from: http://hdl.handle.net/1928/24336

4. -7585-6925. Distributed and dynamic factor modeling of online data.

Degree: PhD, Electrical and Computer Engineering, 2017, University of Texas – Austin

URL: http://hdl.handle.net/2152/62065

► The domain of data mining and machine learning has expanded rapidly in recent years to include both large-scale distributed and streaming computation. Although many open-source… (more)

▼ The domain of data mining and machine learning has expanded rapidly in recent years to include both large-scale distributed and streaming computation. Although many open-source and cloud-based frameworks are available for these tasks, many of which are used in-production by industry, this is a rapidly-evolving technology landscape, and the gap between the academic role of algorithm development and discovery and code available for use with real-world data has grown. In addition, although there is a rich history of mathematical models for streaming data on continuous vector spaces, there has been significantly less work on streaming discrete spaces. However, much if not most of the data available online is composed of high-dimensional sparse counts, such as text corpora and interaction networks. We attempt to help bridge this gap by extending promising Bayesian Poisson factorization and co-factorization models that can be used, for example, to model not only text corpora but also related user interactions in a social network. We construct a dependent process prior that enables dynamic latent factor modeling in the natural probability space of the factors, rather than in the raw data. These models are then scaled to and implemented for distributed compute systems and streaming data. We develop an adaptive hashing method (AdaHash) for lambda architectures that can use latent factors calculated during periodic batch mode updates as a similarity metric for hierarchical grouping, or for finding similar factors to reconcile parameters in a distributed compute scenario. In addition, we develop a novel Hidden Markov variant using particle filters to update prior factors and probabilistically group with new factors in a dynamic inference model (D-GaPS). We show experimentally that the distributed model converges to similar factors as single-process inference, and the dynamic model yields superior quality topics over batch mode alternatives. Empirical studies are presented on the use of a U.S. Senate voting and bill summary data set that is readily interpretable with regard to latent factors. Advisors/Committee Members: Ghosh, Joydeep (advisor), Khurshid, Sarfraz (committee member), Julien, Christine (committee member), Sanghavi, Sujay (committee member), Chakrabarti, Deepayan (committee member).

Subjects/Keywords: Distributed clustering; Dynamic clustering; Matrix factorization; Co-factorization

11 more images…

Record Details Similar Records Cite « Share

❌

APA · Chicago · MLA · Vancouver · CSE | Export to Zotero / EndNote / Reference Manager

APA (6^th Edition):

-7585-6925. (2017). Distributed and dynamic factor modeling of online data. (Doctoral Dissertation). University of Texas – Austin. Retrieved from http://hdl.handle.net/2152/62065

Note: this citation may be lacking information needed for this citation format:
Author name may be incomplete

Chicago Manual of Style (16^th Edition):

-7585-6925. “Distributed and dynamic factor modeling of online data.” 2017. Doctoral Dissertation, University of Texas – Austin. Accessed April 10, 2021. http://hdl.handle.net/2152/62065.

Note: this citation may be lacking information needed for this citation format:
Author name may be incomplete

MLA Handbook (7^th Edition):

-7585-6925. “Distributed and dynamic factor modeling of online data.” 2017. Web. 10 Apr 2021.

Note: this citation may be lacking information needed for this citation format:
Author name may be incomplete

Vancouver:

-7585-6925. Distributed and dynamic factor modeling of online data. [Internet] [Doctoral dissertation]. University of Texas – Austin; 2017. [cited 2021 Apr 10]. Available from: http://hdl.handle.net/2152/62065.

Note: this citation may be lacking information needed for this citation format:
Author name may be incomplete

Council of Science Editors:

-7585-6925. Distributed and dynamic factor modeling of online data. [Doctoral Dissertation]. University of Texas – Austin; 2017. Available from: http://hdl.handle.net/2152/62065

Note: this citation may be lacking information needed for this citation format:
Author name may be incomplete

NSYSU

5. Chang, Cheng-Jui. Cuisine Discovery based on Recipe-Ingredient Network and Matrix Factorization.

Degree: Master, Information Management, 2017, NSYSU

URL: http://etd.lib.nsysu.edu.tw/ETD-db/ETD-search/view_etd?URN=etd-0812117-134940

► This research proposes an approach to find the cuisines, the types of dishes, from the recipes, ingredients and methods of producing dishes. We believe that… (more)

Subjects/Keywords: clustering; network; recommendation; matrix factorization; text mining

Record Details Similar Records Cite « Share

❌

APA · Chicago · MLA · Vancouver · CSE | Export to Zotero / EndNote / Reference Manager

APA (6^th Edition):

Chang, C. (2017). Cuisine Discovery based on Recipe-Ingredient Network and Matrix Factorization. (Thesis). NSYSU. Retrieved from http://etd.lib.nsysu.edu.tw/ETD-db/ETD-search/view_etd?URN=etd-0812117-134940

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

Chicago Manual of Style (16^th Edition):

Chang, Cheng-Jui. “Cuisine Discovery based on Recipe-Ingredient Network and Matrix Factorization.” 2017. Thesis, NSYSU. Accessed April 10, 2021. http://etd.lib.nsysu.edu.tw/ETD-db/ETD-search/view_etd?URN=etd-0812117-134940.

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

MLA Handbook (7^th Edition):

Chang, Cheng-Jui. “Cuisine Discovery based on Recipe-Ingredient Network and Matrix Factorization.” 2017. Web. 10 Apr 2021.

Vancouver:

Chang C. Cuisine Discovery based on Recipe-Ingredient Network and Matrix Factorization. [Internet] [Thesis]. NSYSU; 2017. [cited 2021 Apr 10]. Available from: http://etd.lib.nsysu.edu.tw/ETD-db/ETD-search/view_etd?URN=etd-0812117-134940.

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

Council of Science Editors:

Chang C. Cuisine Discovery based on Recipe-Ingredient Network and Matrix Factorization. [Thesis]. NSYSU; 2017. Available from: http://etd.lib.nsysu.edu.tw/ETD-db/ETD-search/view_etd?URN=etd-0812117-134940

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

Northeastern University

6. Wang, Yueyang. New initialization strategy for nonnegative matrix factorization.

Degree: MS, Department of Electrical and Computer Engineering, 2018, Northeastern University

URL: http://hdl.handle.net/2047/D20290549

► Nonnegative matrix factorization (NMF) has been proved to be a powerful data representa-tion method, and has shown success in applications such as data representation and… (more)

Subjects/Keywords: complementary elements; nonnegative matrix factorization; data

Record Details Similar Records Cite « Share

❌

APA · Chicago · MLA · Vancouver · CSE | Export to Zotero / EndNote / Reference Manager

APA (6^th Edition):

Wang, Y. (2018). New initialization strategy for nonnegative matrix factorization. (Masters Thesis). Northeastern University. Retrieved from http://hdl.handle.net/2047/D20290549

Chicago Manual of Style (16^th Edition):

Wang, Yueyang. “New initialization strategy for nonnegative matrix factorization.” 2018. Masters Thesis, Northeastern University. Accessed April 10, 2021. http://hdl.handle.net/2047/D20290549.

MLA Handbook (7^th Edition):

Wang, Yueyang. “New initialization strategy for nonnegative matrix factorization.” 2018. Web. 10 Apr 2021.

Vancouver:

Wang Y. New initialization strategy for nonnegative matrix factorization. [Internet] [Masters thesis]. Northeastern University; 2018. [cited 2021 Apr 10]. Available from: http://hdl.handle.net/2047/D20290549.

Council of Science Editors:

Wang Y. New initialization strategy for nonnegative matrix factorization. [Masters Thesis]. Northeastern University; 2018. Available from: http://hdl.handle.net/2047/D20290549

University of Minnesota

7. Mosesov, Artem. Adaptive Non-negative Least Squares with Applications to Non-Negative Matrix Factorization.

Degree: M.S.E.E., Electrical Engineering, 2014, University of Minnesota

URL: http://hdl.handle.net/11299/173949

► Problems with non-negativity constrains have recently attracted a great deal of interest. Non-negativity constraints arise naturally in many applications, and are often necessary for proper… (more)

Subjects/Keywords: least squares; matrix factorization; NMF; NNLS; Nonnegative

Record Details Similar Records Cite « Share

❌

APA · Chicago · MLA · Vancouver · CSE | Export to Zotero / EndNote / Reference Manager

APA (6^th Edition):

Mosesov, A. (2014). Adaptive Non-negative Least Squares with Applications to Non-Negative Matrix Factorization. (Masters Thesis). University of Minnesota. Retrieved from http://hdl.handle.net/11299/173949

Chicago Manual of Style (16^th Edition):

Mosesov, Artem. “Adaptive Non-negative Least Squares with Applications to Non-Negative Matrix Factorization.” 2014. Masters Thesis, University of Minnesota. Accessed April 10, 2021. http://hdl.handle.net/11299/173949.

MLA Handbook (7^th Edition):

Mosesov, Artem. “Adaptive Non-negative Least Squares with Applications to Non-Negative Matrix Factorization.” 2014. Web. 10 Apr 2021.

Vancouver:

Mosesov A. Adaptive Non-negative Least Squares with Applications to Non-Negative Matrix Factorization. [Internet] [Masters thesis]. University of Minnesota; 2014. [cited 2021 Apr 10]. Available from: http://hdl.handle.net/11299/173949.

Council of Science Editors:

Mosesov A. Adaptive Non-negative Least Squares with Applications to Non-Negative Matrix Factorization. [Masters Thesis]. University of Minnesota; 2014. Available from: http://hdl.handle.net/11299/173949

University of New South Wales

8. Luo, Cheng. Temporal Dynamics in Recommender Systems.

Degree: Computer Science & Engineering, 2016, University of New South Wales

URL: http://handle.unsw.edu.au/1959.4/55939 ; https://unsworks.unsw.edu.au/fapi/datastream/unsworks:39683/SOURCE02?view=true

► In real-world scenarios, user preferences for items are constantly drifting over time as item perception and popularity are changing when new fashions or products emerge.… (more)

▼ In real-world scenarios, user preferences for items are constantly drifting over time as item perception and popularity are changing when new fashions or products emerge. The ability to model the tendency of both user preferences and item attractiveness is thus vital to the design of recommender systems (RSs). However, conventional methods in RSs are incapable of modeling such a tendency accordingly, leading to an unsatisfactory recommendation performance. This thesis proposes a framework for the temporal dynamics problem in RSs. The temporal properties and dynamic information in user preferences and item attractiveness derived from user feedback over items are modeled, learned and applied to predict user preferences on items over time. The framework provides original solutions to improve the performance of RSs by incorporating and exploiting this significant but traditionally neglected information. Firstly, a novel probabilistic temporal model for RSs is developed to tackle the inherent nonlinear and non-Gaussian dynamic problem with the complex and diverse real-world recommendation scenarios. It tracks simultaneously latent factors that represent user preferences and item attractiveness. A learning and inference algorithm combining a sequential Monte Carlo method and the Expectation-Maximization algorithm for this model is developed to tackle the top-k recommendation problem over time. Secondly, a novel probabilistic personalized and item-wise temporal model is proposed to solve the cold start transition (CST) problem by collaborative tendencies without any prior assumptions about the structure of the dynamics. The CST problem is first defined in this thesis, which is a result that users often leave feedback on an item only once and on only one period, preventing from learning any dynamics directly. Finally, a Bayesian Wishart matrix factorization method is proposed to model the temporal dynamics of variances due to sudden changes and other local temporal effects among user preferences and item attractiveness. It combines the collapsed Gibbs sampling method and the elliptical slice sampling method.The presented models and learning algorithms are validated experimentally on several real-world public benchmark datasets. The experimental results demonstrate that those models and algorithms significantly outperform a variety of state-of-art methods in RSs. Advisors/Committee Members: Cai, Xiongcai, Computer Science & Engineering, Faculty of Engineering, UNSW.

Subjects/Keywords: matrix factorization; recommender systems; temporal dynamics

Record Details Similar Records Cite « Share

❌

APA · Chicago · MLA · Vancouver · CSE | Export to Zotero / EndNote / Reference Manager

APA (6^th Edition):

Luo, C. (2016). Temporal Dynamics in Recommender Systems. (Doctoral Dissertation). University of New South Wales. Retrieved from http://handle.unsw.edu.au/1959.4/55939 ; https://unsworks.unsw.edu.au/fapi/datastream/unsworks:39683/SOURCE02?view=true

Chicago Manual of Style (16^th Edition):

Luo, Cheng. “Temporal Dynamics in Recommender Systems.” 2016. Doctoral Dissertation, University of New South Wales. Accessed April 10, 2021. http://handle.unsw.edu.au/1959.4/55939 ; https://unsworks.unsw.edu.au/fapi/datastream/unsworks:39683/SOURCE02?view=true.

MLA Handbook (7^th Edition):

Luo, Cheng. “Temporal Dynamics in Recommender Systems.” 2016. Web. 10 Apr 2021.

Vancouver:

Luo C. Temporal Dynamics in Recommender Systems. [Internet] [Doctoral dissertation]. University of New South Wales; 2016. [cited 2021 Apr 10]. Available from: http://handle.unsw.edu.au/1959.4/55939 ; https://unsworks.unsw.edu.au/fapi/datastream/unsworks:39683/SOURCE02?view=true.

Council of Science Editors:

Luo C. Temporal Dynamics in Recommender Systems. [Doctoral Dissertation]. University of New South Wales; 2016. Available from: http://handle.unsw.edu.au/1959.4/55939 ; https://unsworks.unsw.edu.au/fapi/datastream/unsworks:39683/SOURCE02?view=true

University of Texas – Austin

9. Yu, Hsiang-Fu. Scalable algorithms for latent variable models in machine learning.

Degree: PhD, Computer science, 2016, University of Texas – Austin

URL: http://hdl.handle.net/2152/41635

► Latent variable modeling (LVM) is a popular approach in many machine learning applications, such as recommender systems and topic modeling, due to its ability to… (more)

Subjects/Keywords: Latent variable modeling; Matrix factorization; Algorithms; Data

Record Details Similar Records Cite « Share

❌

APA · Chicago · MLA · Vancouver · CSE | Export to Zotero / EndNote / Reference Manager

APA (6^th Edition):

Yu, H. (2016). Scalable algorithms for latent variable models in machine learning. (Doctoral Dissertation). University of Texas – Austin. Retrieved from http://hdl.handle.net/2152/41635

Chicago Manual of Style (16^th Edition):

Yu, Hsiang-Fu. “Scalable algorithms for latent variable models in machine learning.” 2016. Doctoral Dissertation, University of Texas – Austin. Accessed April 10, 2021. http://hdl.handle.net/2152/41635.

MLA Handbook (7^th Edition):

Yu, Hsiang-Fu. “Scalable algorithms for latent variable models in machine learning.” 2016. Web. 10 Apr 2021.

Vancouver:

Yu H. Scalable algorithms for latent variable models in machine learning. [Internet] [Doctoral dissertation]. University of Texas – Austin; 2016. [cited 2021 Apr 10]. Available from: http://hdl.handle.net/2152/41635.

Council of Science Editors:

Yu H. Scalable algorithms for latent variable models in machine learning. [Doctoral Dissertation]. University of Texas – Austin; 2016. Available from: http://hdl.handle.net/2152/41635

University of Cincinnati

10. Li, Kendrick T. Group Convex Orthogonal Non-negative Matrix Tri-Factorization with Applications in FC Fingerprinting.

Degree: MS, Engineering and Applied Science: Computer Engineering, 2020, University of Cincinnati

URL: http://rave.ohiolink.edu/etdc/view?acc_num=ucin1592136688034675

► Functional magnetic resonance imaging (fMRI) data has been collected and studied in the neuroscience community for more than two decades. Methods have been developed to… (more)

▼ Functional magnetic resonance imaging (fMRI) data has been collected and studied in the neuroscience community for more than two decades. Methods have been developed to model fMRI data as a network, referred to as a functional connectivity (FC) network, consisting of a matrix of pairwise correlation of the blood-oxygen-level-dependent (BOLD) signal measured at different brain regions.FC fingerprinting is a recently introduced problem where the goal is to identify subjects based on FC. Given reference fMRI scans from a set of subjects and an unidentified target fMRI scan from a subject in this set, the goal is to identify which subject the target scan was collected from by computing the correlation between the target FC and the reference FCs. The reference FC with the highest similarity is identified as the target FC. FC fingerprinting studies have reported near 100% accuracies, suggesting that the FC captures subject-specific neuronal activity signature effectively. However, recently we and others have shown that fingerprinting accuracy decreases as the number of subjects increases. Our previous work provided multiple contributions in the context of the FC fingerprinting problem. We showed using silhouette analysis that the reason for the decrease in FC fingerprinting accuracy was due to cluttering of FCs in high-dimensional space. We introduced an intelligent feature selection framework which used a subset of the elements in the FC to improve accuracy. We observed that effective features exhibited a block structure where connectivity between certain groups of regions were more effective for fingerprinting than others. In this thesis our objective is to extract a group-level block-structure from FCs where block-level connectivity can then be used for fingerprinting. One promising direction is to use a non-negative matrix factorization (NMF), a data modeling tool used to extract the inherent structure in data. One variant of NMF, fast matrix tri-factorization (Fast-MtF), allows us to extract the block structure from FC. However, Fast-MtF is incapable of utilizing group-level information to discover a group-level block structure for our dataset. Group-MtF methods, such as linked matrix factorization (LMF) and RESCAL, utilize group-level information. Unfortunately, they lack orthogonality and non-negativity constraints for extracting a block-structure.We developed a new problem formulation, Group convex orthogonaL non-nEgative mAtrix tri-factorizatioN (GLEAN), to capture a group-level block-structure for a group of mixed-sign matrices. By enforcing orthogonality and non-negativity constraints, we formulated a group `convex' model which finds the group-level block-structure . We developed a gradient-descent based approach to solve the GLEAN formulation.To evaluate GLEAN, we conducted two experiments: 1) a comparative analysis between GLEAN and state-of-the-art MtF methods on their effectiveness in finding the ground-truth block-structure from a synthetic dataset and 2) a comparative analysis between GLEAN and group… Advisors/Committee Members: Atluri, Gowtham (Committee Chair).

Subjects/Keywords: Computer Science; fMRI; Functional connectivity; FC fingerprinting; Matrix tri-factorization; Group matrix tri-factorization

Record Details Similar Records Cite « Share

❌

APA · Chicago · MLA · Vancouver · CSE | Export to Zotero / EndNote / Reference Manager

APA (6^th Edition):

Li, K. T. (2020). Group Convex Orthogonal Non-negative Matrix Tri-Factorization with Applications in FC Fingerprinting. (Masters Thesis). University of Cincinnati. Retrieved from http://rave.ohiolink.edu/etdc/view?acc_num=ucin1592136688034675

Chicago Manual of Style (16^th Edition):

Li, Kendrick T. “Group Convex Orthogonal Non-negative Matrix Tri-Factorization with Applications in FC Fingerprinting.” 2020. Masters Thesis, University of Cincinnati. Accessed April 10, 2021. http://rave.ohiolink.edu/etdc/view?acc_num=ucin1592136688034675.

MLA Handbook (7^th Edition):

Li, Kendrick T. “Group Convex Orthogonal Non-negative Matrix Tri-Factorization with Applications in FC Fingerprinting.” 2020. Web. 10 Apr 2021.

Vancouver:

Li KT. Group Convex Orthogonal Non-negative Matrix Tri-Factorization with Applications in FC Fingerprinting. [Internet] [Masters thesis]. University of Cincinnati; 2020. [cited 2021 Apr 10]. Available from: http://rave.ohiolink.edu/etdc/view?acc_num=ucin1592136688034675.

Council of Science Editors:

Li KT. Group Convex Orthogonal Non-negative Matrix Tri-Factorization with Applications in FC Fingerprinting. [Masters Thesis]. University of Cincinnati; 2020. Available from: http://rave.ohiolink.edu/etdc/view?acc_num=ucin1592136688034675

University of Minnesota

11. Sun, Ruoyu. Matrix Completion via Nonconvex Factorization: Algorithms and Theory.

Degree: PhD, Electrical/Computer Engineering, 2015, University of Minnesota

URL: http://hdl.handle.net/11299/175344

► Learning low-rank structure of the data matrix is a powerful method to deal with ``big data''. However, in many modern applications such as recommendation systems… (more)

▼ Learning low-rank structure of the data matrix is a powerful method to deal with ``big data''. However, in many modern applications such as recommendation systems and sensor localization, it is impossible or too costly to obtain all data, resulting in a data matrix with most entries missing. A problem of great interest is then to infer the missing data based on very few observations, usually under the assumption that the true data matrix is low rank, which is widely known as the matrix completion problem. The most popular solution for large-scale matrix completion is the matrix factorization (MF) formulation,which has achieved great empirical success. However, due to the non-convexity caused by the factorization model, little is known about whether and when the algorithms for the MF formulation will generate a good solution. In this thesis, we will study the non convex MF formulation for matrix completion, both algorithmically and theoretically. First, we empirically analyze several standard algorithms for the MF formulation. We present a novel finding that the recovery ability of an algorithm mainly depends on whether it can control the row-norms (or incoherence constants) of the iterates. Motivated by this finding, we propose a new formulation that either adds constraints or penalty-function-type regularizers to directly control the row-norms. Simulation results show that the algorithms for the new formulation can recover the matrix in the regime very close to the fundamental limit, outperforming the standard algorithms. We then establish a theoretical guarantee for the new MF formulation to correctly recover the underlying low-rank matrix. In particular, we show that under similar conditions to those in previous works, many standard optimization algorithms converge to the global optima of the new MF formulation, and recover the true low-rank matrix. This result is rather surprising since we prove convergence to global optima for a nonconvex problem. To the best of our knowledge, our result is the first one that provides exact recovery guarantee for many standard algorithms. A major difference of our work from the existing results is that we do not need resampling (i.e., using independent samples at each iteration) in either the algorithm or its analysis. Technically, we develop a novel perturbation analysis for matrix factorization which may be of independent interest.

Subjects/Keywords: alternating minimization; matrix completion; matrix factorization; nonconvex; optimization; SGD

Record Details Similar Records Cite « Share

❌

APA · Chicago · MLA · Vancouver · CSE | Export to Zotero / EndNote / Reference Manager

APA (6^th Edition):

Sun, R. (2015). Matrix Completion via Nonconvex Factorization: Algorithms and Theory. (Doctoral Dissertation). University of Minnesota. Retrieved from http://hdl.handle.net/11299/175344

Chicago Manual of Style (16^th Edition):

Sun, Ruoyu. “Matrix Completion via Nonconvex Factorization: Algorithms and Theory.” 2015. Doctoral Dissertation, University of Minnesota. Accessed April 10, 2021. http://hdl.handle.net/11299/175344.

MLA Handbook (7^th Edition):

Sun, Ruoyu. “Matrix Completion via Nonconvex Factorization: Algorithms and Theory.” 2015. Web. 10 Apr 2021.

Vancouver:

Sun R. Matrix Completion via Nonconvex Factorization: Algorithms and Theory. [Internet] [Doctoral dissertation]. University of Minnesota; 2015. [cited 2021 Apr 10]. Available from: http://hdl.handle.net/11299/175344.

Council of Science Editors:

Sun R. Matrix Completion via Nonconvex Factorization: Algorithms and Theory. [Doctoral Dissertation]. University of Minnesota; 2015. Available from: http://hdl.handle.net/11299/175344

University of Technology, Sydney

12. Li, Fangfang. Incorporating couplings into collaborative filtering.

Degree: 2016, University of Technology, Sydney

URL: http://hdl.handle.net/10453/44174

► Recommender Systems (RS) have been proposed to help users tackle information overload by suggesting potentially interesting items to users. A typical RS usually has a… (more)

▼ Recommender Systems (RS) have been proposed to help users tackle information overload by suggesting potentially interesting items to users. A typical RS usually has a set of users and items with various rating preferences. The key task of RS is to predict an unknown rating or to recommend relevant items to a given user. Many existing recommendation methods such as Collaborative Filtering (CF), Content-based Recommendation, and Hybrid Filtering often assume that users, items and their attributes are identically and independently distributed. In the real world, however, these objects and their attributes are often coupled with each other through explicit or implicit relations. On one hand, users are often connected through social or trust relations, and items are interacted with linkage or citation relations. On the other hand, the attributes of users or items are also more or less coupled with each other. These dependent relations clearly demonstrate that the users, items, and their attributes in RS are not identically and independently distributed (non-IID), which is rarely considered in most existing recommendation methods. The non-IID RS have emerged with the consideration of non-IID characteristics into RS. A main challenge in non-IID RS is to analyse and model the coupling relations between users and between items. In this dissertation, we aim to improve recommendation effectiveness by incorporating the coupling relations into RS. The main contributions of the dissertation are summarized as follows: (1) We propose three novel neighbourhood-based CF methods including coupled user-based CF, coupled item-based CF, and coupled CF. Specifically, we first apply a novel coupled object similarity to compute the coupling relations between users and between items based on their attributes. We then integrate the user and item couplings into the neighbourhood-based CF to produce the proposed methods by inventing new similarity measures. (2) We propose three novel model-based CF methods including coupled user-based matrix factorization (CUMF), coupled item-based matrix factorization (CIMF), and coupled matrix factorization (CMF). CUMF and CIMF respectively integrate the attribute-based user couplings and item couplings into MF, and CMF incorporates the user couplings, item couplings, and the user-item rating matrix together into MF. (3) We propose a two-level matrix factorization recommendation model which integrates the textual semantic couplings between items and the user-item rating matrix together. (4) We conduct experiments to evaluate the effectiveness of incorporating the couplings into non-IID RS.

Subjects/Keywords: Recommender Systems (RS).; Collaborative Filtering (CF).; Hybrid Filtering.; Coupling.; Coupled user-based matrix factorization (CUMF).; Coupled item-based matrix factorization (CIMF).; Coupled matrix factorization (CMF).

Record Details Similar Records Cite « Share

❌

APA · Chicago · MLA · Vancouver · CSE | Export to Zotero / EndNote / Reference Manager

APA (6^th Edition):

Li, F. (2016). Incorporating couplings into collaborative filtering. (Thesis). University of Technology, Sydney. Retrieved from http://hdl.handle.net/10453/44174

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

Chicago Manual of Style (16^th Edition):

Li, Fangfang. “Incorporating couplings into collaborative filtering.” 2016. Thesis, University of Technology, Sydney. Accessed April 10, 2021. http://hdl.handle.net/10453/44174.

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

MLA Handbook (7^th Edition):

Li, Fangfang. “Incorporating couplings into collaborative filtering.” 2016. Web. 10 Apr 2021.

Vancouver:

Li F. Incorporating couplings into collaborative filtering. [Internet] [Thesis]. University of Technology, Sydney; 2016. [cited 2021 Apr 10]. Available from: http://hdl.handle.net/10453/44174.

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

Council of Science Editors:

Li F. Incorporating couplings into collaborative filtering. [Thesis]. University of Technology, Sydney; 2016. Available from: http://hdl.handle.net/10453/44174

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

NSYSU

13. Yang, Wan-Chen. Topic Evolution Discovery based on Regularized Matrix Factorization.

Degree: Master, Information Management, 2018, NSYSU

URL: http://etd.lib.nsysu.edu.tw/ETD-db/ETD-search/view_etd?URN=etd-0727118-143310

► In this thesis, we propose Hierarchical Non-negative Matrix Factorization(hNMF) to discover the hierarchical correlation among topics. The topics in lower layers are more concrete, whereas… (more)

Subjects/Keywords: Topic model; Hierarchical model; Non-negative matrix factorization; Hierarchical Non-negative matrix factorization; Topic classification; Topic evolution discovery; Multi-layer topic

Record Details Similar Records Cite « Share

❌

APA · Chicago · MLA · Vancouver · CSE | Export to Zotero / EndNote / Reference Manager

APA (6^th Edition):

Yang, W. (2018). Topic Evolution Discovery based on Regularized Matrix Factorization. (Thesis). NSYSU. Retrieved from http://etd.lib.nsysu.edu.tw/ETD-db/ETD-search/view_etd?URN=etd-0727118-143310

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

Chicago Manual of Style (16^th Edition):

Yang, Wan-Chen. “Topic Evolution Discovery based on Regularized Matrix Factorization.” 2018. Thesis, NSYSU. Accessed April 10, 2021. http://etd.lib.nsysu.edu.tw/ETD-db/ETD-search/view_etd?URN=etd-0727118-143310.

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

MLA Handbook (7^th Edition):

Yang, Wan-Chen. “Topic Evolution Discovery based on Regularized Matrix Factorization.” 2018. Web. 10 Apr 2021.

Vancouver:

Yang W. Topic Evolution Discovery based on Regularized Matrix Factorization. [Internet] [Thesis]. NSYSU; 2018. [cited 2021 Apr 10]. Available from: http://etd.lib.nsysu.edu.tw/ETD-db/ETD-search/view_etd?URN=etd-0727118-143310.

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

Council of Science Editors:

Yang W. Topic Evolution Discovery based on Regularized Matrix Factorization. [Thesis]. NSYSU; 2018. Available from: http://etd.lib.nsysu.edu.tw/ETD-db/ETD-search/view_etd?URN=etd-0727118-143310

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

University of South Africa

14. Gaoseb, Frans Otto. Spectral factorization of matrices .

Degree: 2020, University of South Africa

URL: http://hdl.handle.net/10500/26844

► The research will analyze and compare the current research on the spectral factorization of non-singular and singular matrices. We show that a nonsingular non-scalar matrix… (more)

▼ The research will analyze and compare the current research on the spectral factorization of non-singular and singular matrices. We show that a nonsingular non-scalar matrix A can be written as a product A = BC where the eigenvalues of B and C are arbitrarily prescribed subject to the condition that the product of the eigenvalues of B and C must be equal to the determinant of A. Further, B and C can be simultaneously triangularised as a lower and upper triangular matrix respectively. Singular matrices will be factorized in terms of nilpotent matrices and otherwise over an arbitrary or complex field in order to present an integrated and detailed report on the current state of research in this area. Applications related to unipotent, positive-definite, commutator, involutory and Hermitian factorization are studied for non-singular matrices, while applications related to positive-semidefinite matrices are investigated for singular matrices. We will consider the theorems found in Sourour [24] and Laffey [17] to show that a non-singular non-scalar matrix can be factorized spectrally. The same two articles will be used to show applications to unipotent, positive-definite and commutator factorization. Applications related to Hermitian factorization will be considered in [26]. Laffey [18] shows that a non-singular matrix A with det A = ±1 is a product of four involutions with certain conditions on the arbitrary field. To aid with this conclusion a thorough study is made of Hoffman [13], who shows that an invertible linear transformation T of a finite dimensional vector space over a field is a product of two involutions if and only if T is similar to T−1. Sourour shows in [24] that if A is an n × n matrix over an arbitrary field containing at least n + 2 elements and if det A = ±1, then A is the product of at most four involutions. We will review the work of Wu [29] and show that a singular matrix A of order n ≥ 2 over the complex field can be expressed as a product of two nilpotent matrices, where the rank of each of the factors is the same as A, except when A is a 2 × 2 nilpotent matrix of rank one. Nilpotent factorization of singular matrices over an arbitrary field will also be investigated. Laffey [17] shows that the result of Wu, which he established over the complex field, is also valid over an arbitrary field by making use of a special matrix factorization involving similarity to an LU factorization. His proof is based on an application of Fitting's Lemma to express, up to similarity, a singular matrix as a direct sum of a non-singular and nilpotent matrix, and then to write the non-singular component as a product of a lower and upper triangular matrix using a matrix factorization theorem of Sourour [24]. The main theorem by Sourour and Tang [26] will be investigated to highlight the necessary and sufficient conditions for a singular matrix to be written as a product of two matrices with prescribed eigenvalues. This result is used to prove applications related to positive-semidefinite matrices… Advisors/Committee Members: Botha, J.D (advisor).

Subjects/Keywords: Spectral factorization; Matrix factorization; Singular Matrices; Non-singular matrices; Involutions; Commutators; Unipotent matrices; Positive-definite matrices; Hermitian factorization; Scalar matrices; Nilpotent factorization

Record Details Similar Records Cite « Share

❌

APA · Chicago · MLA · Vancouver · CSE | Export to Zotero / EndNote / Reference Manager

APA (6^th Edition):

Gaoseb, F. O. (2020). Spectral factorization of matrices . (Masters Thesis). University of South Africa. Retrieved from http://hdl.handle.net/10500/26844

Chicago Manual of Style (16^th Edition):

Gaoseb, Frans Otto. “Spectral factorization of matrices .” 2020. Masters Thesis, University of South Africa. Accessed April 10, 2021. http://hdl.handle.net/10500/26844.

MLA Handbook (7^th Edition):

Gaoseb, Frans Otto. “Spectral factorization of matrices .” 2020. Web. 10 Apr 2021.

Vancouver:

Gaoseb FO. Spectral factorization of matrices . [Internet] [Masters thesis]. University of South Africa; 2020. [cited 2021 Apr 10]. Available from: http://hdl.handle.net/10500/26844.

Council of Science Editors:

Gaoseb FO. Spectral factorization of matrices . [Masters Thesis]. University of South Africa; 2020. Available from: http://hdl.handle.net/10500/26844

University of California – Irvine

15. Pezeshkpour, Pouya. Compact Factorization of Matrices Using Generalized Round-Rank.

Degree: Electrical and Computer Engineering, 2018, University of California – Irvine

URL: http://www.escholarship.org/uc/item/9x58b95k

► Matrix factorization is a popular machine learning technique, with applications in variety of domains, such as recommendation systems [16, 28], natural language processing [26], and… (more)

▼ Matrix factorization is a popular machine learning technique, with applications in variety of domains, such as recommendation systems [16, 28], natural language processing [26], and computer vision [10]. Due to this widespread use of these models, there has been considerable theoretical analysis of the various properties of low-rank approximations of real-valued matrices, including approximation rank [1, 5] and sample complexity [2].Rather than assume real-valued data, a number of studies (particularly ones on practical applications) focus on more specific data types, such as binary data [23], integer data [17], and ordinal data [12, 30]. For such matrices, existing approaches have used different link functions, applied in an element-wise manner to the low-rank representation [21], i.e. the output Y is ψ(U^TV) instead of the conventional U^TV. These link functions have been justified from a probabilistic point of view [4, 27], and have provided considerable success in empirical settings. However, theoretical results for linear factorization do not apply here, and thus the expressive power of the factorization models with non-linear link functions is not clear, and neither is the relation of the rank of a matrix to the link function used.In this work, we first define a generalized notion of rank based on the link function ψ, as the rank of a latent matrix before the link function is applied. We focus on a link function that applies to factorization of integer-valued matrices: the generalized round function (GRF), and define the corresponding generalized round-rank (GRR). After providing background on GRR, we show that there are many low-GRR matrices that are full rank [1]. Moreover, we also study the approximation limitations of linear rank, by showing, for example, that low GRR matrices often cannot be approximated by low-rank linear matrices. We define uniqueness for GRR-based matrix completion, and derive its necessary and sufficient conditions. These properties demonstrate that many full linear-rank matrices can be factorized using low-rank matrices if an appropriate link function is used.We also present an empirical evaluation of factorization with different link functions for matrix reconstruction and completion. We show that using link functions is efficient compared to linear rank, in that gradient-based optimization approach learns more accurate reconstructions using a lower rank representation and fewer training samples. We also perform experiments on matrix completion on two recommendation datasets, and demonstrate that appropriate link function outperform linear factorization, thus can play a crucial role in accurate matrix completion.

Subjects/Keywords: Electrical engineering; Computer science; Generalized Round-Rank; Linear Rank; Matrix Completion; Matrix Factorization

Record Details Similar Records Cite « Share

❌

APA · Chicago · MLA · Vancouver · CSE | Export to Zotero / EndNote / Reference Manager

APA (6^th Edition):

Pezeshkpour, P. (2018). Compact Factorization of Matrices Using Generalized Round-Rank. (Thesis). University of California – Irvine. Retrieved from http://www.escholarship.org/uc/item/9x58b95k

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

Chicago Manual of Style (16^th Edition):

Pezeshkpour, Pouya. “Compact Factorization of Matrices Using Generalized Round-Rank.” 2018. Thesis, University of California – Irvine. Accessed April 10, 2021. http://www.escholarship.org/uc/item/9x58b95k.

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

MLA Handbook (7^th Edition):

Pezeshkpour, Pouya. “Compact Factorization of Matrices Using Generalized Round-Rank.” 2018. Web. 10 Apr 2021.

Vancouver:

Pezeshkpour P. Compact Factorization of Matrices Using Generalized Round-Rank. [Internet] [Thesis]. University of California – Irvine; 2018. [cited 2021 Apr 10]. Available from: http://www.escholarship.org/uc/item/9x58b95k.

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

Council of Science Editors:

Pezeshkpour P. Compact Factorization of Matrices Using Generalized Round-Rank. [Thesis]. University of California – Irvine; 2018. Available from: http://www.escholarship.org/uc/item/9x58b95k

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

University of Minnesota

16. Sharma, Mohit. Preference modeling and Accuracy in Recommender Systems.

Degree: PhD, Computer Science, 2017, University of Minnesota

URL: http://hdl.handle.net/11299/192686

► Recommender systems are widely used to recommend the most appealing items to users. In this thesis, we focus on analyzing the accuracy of the state-of-the-art… (more)

▼ Recommender systems are widely used to recommend the most appealing items to users. In this thesis, we focus on analyzing the accuracy of the state-of-the-art matrix completion-based recommendation methods and develop methods to model users' preferences to address different problems that arise in recommender systems. Collaborative filtering-based methods are widely used to generate item recommendations to the user. The low-rank matrix completion method is the state-of-the-art collaborative filtering method. We will show that the accuracy and the ranking performance of matrix completion-based methods are affected by the skewed distribution of ratings in the user-item rating matrix. Additionally, we will illustrate that the number of ratings an item has positively correlates with the prediction accuracy and the ranking performance of the matrix completion approach for the item. Furthermore, we show that the users or the items that are present in the tail, i.e., those having few ratings in real datasets, may not have sufficient ratings to estimate the low-rank models accurately by matrix completion approach. We use these insights to develop TruncatedMF, a matrix completion-based approach that outperforms the state-of-the-art matrix completion method for the users and the items in the tail. Since for new items we do not have any prior preferences from existing users, it is hard to recommend these items to the users. We can use non-collaborative methods that rely on similarities between the new item and the items preferred by a user in the past to model the user preference for the new item. However, these methods consider the item features independently and ignore the interactions among the features of the items while computing the similarities. Modeling the interactions among features can provide more information towards the relevance of an item in comparison to the scenario when the features are considered independently. We develop a new method called User-specific Feature-based factorized Bilinear Similarity Model (UFBSM), that uses all available information across users to capture these interactions among features and learns a low-rank user personalized bilinear similarity model for the Top-n recommendation of new items. In addition to providing ratings over individual items, the users can also provide ratings on sets of items. A rating provided by a user on a set of items conveys some preference information about the items in the set and enables us to acquire a user’s preferences for more items that the number of ratings that the user provided. Moreover, users may have privacy concerns and hence may not be willing to indicate their preferences on individual items explicitly but may be willing to provide a rating to a set of items, as it provides some level of information hiding. We will investigate how do users’ item-level preferences relate to their set-level preferences. Also, we will introduce collaborative filtering-based methods that explicitly model the user behavior of providing ratings on sets of…

Subjects/Keywords: Cold-Start item recommendations; Collaborative filtering; Group of items; Matrix completion; Matrix factorization; Recommender systems

Record Details Similar Records Cite « Share

❌

APA · Chicago · MLA · Vancouver · CSE | Export to Zotero / EndNote / Reference Manager

APA (6^th Edition):

Sharma, M. (2017). Preference modeling and Accuracy in Recommender Systems. (Doctoral Dissertation). University of Minnesota. Retrieved from http://hdl.handle.net/11299/192686

Chicago Manual of Style (16^th Edition):

Sharma, Mohit. “Preference modeling and Accuracy in Recommender Systems.” 2017. Doctoral Dissertation, University of Minnesota. Accessed April 10, 2021. http://hdl.handle.net/11299/192686.

MLA Handbook (7^th Edition):

Sharma, Mohit. “Preference modeling and Accuracy in Recommender Systems.” 2017. Web. 10 Apr 2021.

Vancouver:

Sharma M. Preference modeling and Accuracy in Recommender Systems. [Internet] [Doctoral dissertation]. University of Minnesota; 2017. [cited 2021 Apr 10]. Available from: http://hdl.handle.net/11299/192686.

Council of Science Editors:

Sharma M. Preference modeling and Accuracy in Recommender Systems. [Doctoral Dissertation]. University of Minnesota; 2017. Available from: http://hdl.handle.net/11299/192686

NSYSU

17. Ma, Chuan-yuan. Combining Co-Ratings and Trust Relationships on Social Networks for Collaborative Recommendation.

Degree: Master, Information Management, 2014, NSYSU

URL: http://etd.lib.nsysu.edu.tw/ETD-db/ETD-search/view_etd?URN=etd-0629114-113648

► It becomes a more and more popular approach to develop recommendation systems based on trust relationships on the social networks. While social information that explicitly… (more)

Subjects/Keywords: K-Nearest Neighbor; Trust Transitivity; Distrust; Matrix Factorization; In-Degree

Record Details Similar Records Cite « Share

❌

APA · Chicago · MLA · Vancouver · CSE | Export to Zotero / EndNote / Reference Manager

APA (6^th Edition):

Ma, C. (2014). Combining Co-Ratings and Trust Relationships on Social Networks for Collaborative Recommendation. (Thesis). NSYSU. Retrieved from http://etd.lib.nsysu.edu.tw/ETD-db/ETD-search/view_etd?URN=etd-0629114-113648

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

Chicago Manual of Style (16^th Edition):

Ma, Chuan-yuan. “Combining Co-Ratings and Trust Relationships on Social Networks for Collaborative Recommendation.” 2014. Thesis, NSYSU. Accessed April 10, 2021. http://etd.lib.nsysu.edu.tw/ETD-db/ETD-search/view_etd?URN=etd-0629114-113648.

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

MLA Handbook (7^th Edition):

Ma, Chuan-yuan. “Combining Co-Ratings and Trust Relationships on Social Networks for Collaborative Recommendation.” 2014. Web. 10 Apr 2021.

Vancouver:

Ma C. Combining Co-Ratings and Trust Relationships on Social Networks for Collaborative Recommendation. [Internet] [Thesis]. NSYSU; 2014. [cited 2021 Apr 10]. Available from: http://etd.lib.nsysu.edu.tw/ETD-db/ETD-search/view_etd?URN=etd-0629114-113648.

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

Council of Science Editors:

Ma C. Combining Co-Ratings and Trust Relationships on Social Networks for Collaborative Recommendation. [Thesis]. NSYSU; 2014. Available from: http://etd.lib.nsysu.edu.tw/ETD-db/ETD-search/view_etd?URN=etd-0629114-113648

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

NSYSU

18. Tseng, Kuan-Yu. Context-aware Collaborative Filtering Methods for Multimedia Recommendation.

Degree: Master, Information Management, 2014, NSYSU

URL: http://etd.lib.nsysu.edu.tw/ETD-db/ETD-search/view_etd?URN=etd-0629114-122019

► The rapid development of mobile device and multimedia allows us today to have extremely rich multimedia information sources. The numbers of data also increase rapidly… (more)

Subjects/Keywords: Mobile Device; Collaborative Filtering; Matrix Factorization; Context-Awareness; Recommender System

Record Details Similar Records Cite « Share

❌

APA · Chicago · MLA · Vancouver · CSE | Export to Zotero / EndNote / Reference Manager

APA (6^th Edition):

Tseng, K. (2014). Context-aware Collaborative Filtering Methods for Multimedia Recommendation. (Thesis). NSYSU. Retrieved from http://etd.lib.nsysu.edu.tw/ETD-db/ETD-search/view_etd?URN=etd-0629114-122019

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

Chicago Manual of Style (16^th Edition):

Tseng, Kuan-Yu. “Context-aware Collaborative Filtering Methods for Multimedia Recommendation.” 2014. Thesis, NSYSU. Accessed April 10, 2021. http://etd.lib.nsysu.edu.tw/ETD-db/ETD-search/view_etd?URN=etd-0629114-122019.

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

MLA Handbook (7^th Edition):

Tseng, Kuan-Yu. “Context-aware Collaborative Filtering Methods for Multimedia Recommendation.” 2014. Web. 10 Apr 2021.

Vancouver:

Tseng K. Context-aware Collaborative Filtering Methods for Multimedia Recommendation. [Internet] [Thesis]. NSYSU; 2014. [cited 2021 Apr 10]. Available from: http://etd.lib.nsysu.edu.tw/ETD-db/ETD-search/view_etd?URN=etd-0629114-122019.

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

Council of Science Editors:

Tseng K. Context-aware Collaborative Filtering Methods for Multimedia Recommendation. [Thesis]. NSYSU; 2014. Available from: http://etd.lib.nsysu.edu.tw/ETD-db/ETD-search/view_etd?URN=etd-0629114-122019

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

NSYSU

19. Hsieh, Sung-chen. Computing the Numerical Nullity of Sylvester Matrix of Univariate Polynomials.

Degree: Master, Applied Mathematics, 2014, NSYSU

URL: http://etd.lib.nsysu.edu.tw/ETD-db/ETD-search/view_etd?URN=etd-1117114-104741

► Computing the greatest common divisor (GCD) of univariate polynomials is one of the fundamental algebraic problems with a long history. The classical Euclidean algorithm is… (more)

Subjects/Keywords: numerical nullity; polynomial; greatest common divisor; Sylvester matrix; QR-factorization

Record Details Similar Records Cite « Share

❌

APA · Chicago · MLA · Vancouver · CSE | Export to Zotero / EndNote / Reference Manager

APA (6^th Edition):

Hsieh, S. (2014). Computing the Numerical Nullity of Sylvester Matrix of Univariate Polynomials. (Thesis). NSYSU. Retrieved from http://etd.lib.nsysu.edu.tw/ETD-db/ETD-search/view_etd?URN=etd-1117114-104741

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

Chicago Manual of Style (16^th Edition):

Hsieh, Sung-chen. “Computing the Numerical Nullity of Sylvester Matrix of Univariate Polynomials.” 2014. Thesis, NSYSU. Accessed April 10, 2021. http://etd.lib.nsysu.edu.tw/ETD-db/ETD-search/view_etd?URN=etd-1117114-104741.

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

MLA Handbook (7^th Edition):

Hsieh, Sung-chen. “Computing the Numerical Nullity of Sylvester Matrix of Univariate Polynomials.” 2014. Web. 10 Apr 2021.

Vancouver:

Hsieh S. Computing the Numerical Nullity of Sylvester Matrix of Univariate Polynomials. [Internet] [Thesis]. NSYSU; 2014. [cited 2021 Apr 10]. Available from: http://etd.lib.nsysu.edu.tw/ETD-db/ETD-search/view_etd?URN=etd-1117114-104741.

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

Council of Science Editors:

Hsieh S. Computing the Numerical Nullity of Sylvester Matrix of Univariate Polynomials. [Thesis]. NSYSU; 2014. Available from: http://etd.lib.nsysu.edu.tw/ETD-db/ETD-search/view_etd?URN=etd-1117114-104741

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

NSYSU

20. Yang, Tsung-Lin. Combining Trust Relationships and Super Users for Collaborative Recommendation.

Degree: Master, Information Management, 2017, NSYSU

URL: http://etd.lib.nsysu.edu.tw/ETD-db/ETD-search/view_etd?URN=etd-0113117-153742

► The network and mobile communication develop very quickly in recent years. We could get the data easily online. However, the speed of data transformation is… (more)

Subjects/Keywords: Collaborative Filtering; Recommendation System; Cold Start; Matrix Factorization; Trust

Record Details Similar Records Cite « Share

❌

APA · Chicago · MLA · Vancouver · CSE | Export to Zotero / EndNote / Reference Manager

APA (6^th Edition):

Yang, T. (2017). Combining Trust Relationships and Super Users for Collaborative Recommendation. (Thesis). NSYSU. Retrieved from http://etd.lib.nsysu.edu.tw/ETD-db/ETD-search/view_etd?URN=etd-0113117-153742

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

Chicago Manual of Style (16^th Edition):

Yang, Tsung-Lin. “Combining Trust Relationships and Super Users for Collaborative Recommendation.” 2017. Thesis, NSYSU. Accessed April 10, 2021. http://etd.lib.nsysu.edu.tw/ETD-db/ETD-search/view_etd?URN=etd-0113117-153742.

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

MLA Handbook (7^th Edition):

Yang, Tsung-Lin. “Combining Trust Relationships and Super Users for Collaborative Recommendation.” 2017. Web. 10 Apr 2021.

Vancouver:

Yang T. Combining Trust Relationships and Super Users for Collaborative Recommendation. [Internet] [Thesis]. NSYSU; 2017. [cited 2021 Apr 10]. Available from: http://etd.lib.nsysu.edu.tw/ETD-db/ETD-search/view_etd?URN=etd-0113117-153742.

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

Council of Science Editors:

Yang T. Combining Trust Relationships and Super Users for Collaborative Recommendation. [Thesis]. NSYSU; 2017. Available from: http://etd.lib.nsysu.edu.tw/ETD-db/ETD-search/view_etd?URN=etd-0113117-153742

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

NSYSU

21. Wang, Shih-hao. Using Cloud Computing to Improve the Efficiency and Effectiveness of Matrix Factorization : A Case Study of Context-aware Data Set.

Degree: Master, Information Management, 2017, NSYSU

URL: http://etd.lib.nsysu.edu.tw/ETD-db/ETD-search/view_etd?URN=etd-0221117-203746

► There are two types of methods often used to develop collaborative recommender systems. One is based on the similarity calculation and the other is based… (more)

Subjects/Keywords: Context Aware; Matrix Factorization; Cloud Computing; Recommended System; Collaborative Filtering

Record Details Similar Records Cite « Share

❌

APA · Chicago · MLA · Vancouver · CSE | Export to Zotero / EndNote / Reference Manager

APA (6^th Edition):

Wang, S. (2017). Using Cloud Computing to Improve the Efficiency and Effectiveness of Matrix Factorization : A Case Study of Context-aware Data Set. (Thesis). NSYSU. Retrieved from http://etd.lib.nsysu.edu.tw/ETD-db/ETD-search/view_etd?URN=etd-0221117-203746

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

Chicago Manual of Style (16^th Edition):

Wang, Shih-hao. “Using Cloud Computing to Improve the Efficiency and Effectiveness of Matrix Factorization : A Case Study of Context-aware Data Set.” 2017. Thesis, NSYSU. Accessed April 10, 2021. http://etd.lib.nsysu.edu.tw/ETD-db/ETD-search/view_etd?URN=etd-0221117-203746.

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

MLA Handbook (7^th Edition):

Wang, Shih-hao. “Using Cloud Computing to Improve the Efficiency and Effectiveness of Matrix Factorization : A Case Study of Context-aware Data Set.” 2017. Web. 10 Apr 2021.

Vancouver:

Wang S. Using Cloud Computing to Improve the Efficiency and Effectiveness of Matrix Factorization : A Case Study of Context-aware Data Set. [Internet] [Thesis]. NSYSU; 2017. [cited 2021 Apr 10]. Available from: http://etd.lib.nsysu.edu.tw/ETD-db/ETD-search/view_etd?URN=etd-0221117-203746.

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

Council of Science Editors:

Wang S. Using Cloud Computing to Improve the Efficiency and Effectiveness of Matrix Factorization : A Case Study of Context-aware Data Set. [Thesis]. NSYSU; 2017. Available from: http://etd.lib.nsysu.edu.tw/ETD-db/ETD-search/view_etd?URN=etd-0221117-203746

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

Dalhousie University

22. Toganassova, Dilyara. SOURCE APPORTIONMENT OF PM2.5 SHIP EMISSIONS IN HALIFAX, NOVA SCOTIA, CANADA.

Degree: Master of Applied Science, Department of Environmental Engineering, 2013, Dalhousie University

URL: http://hdl.handle.net/10222/21432

► This study investigated the source attribution of ship emissions to atmospheric particulate matter with a median aerodynamic diameter less than, or equal to 2.5 micron… (more)

Subjects/Keywords: Source apportionment; PM2.5; USEPA Positive Matrix Factorization; sources (factors)

Record Details Similar Records Cite « Share

❌

APA · Chicago · MLA · Vancouver · CSE | Export to Zotero / EndNote / Reference Manager

APA (6^th Edition):

Toganassova, D. (2013). SOURCE APPORTIONMENT OF PM2.5 SHIP EMISSIONS IN HALIFAX, NOVA SCOTIA, CANADA. (Masters Thesis). Dalhousie University. Retrieved from http://hdl.handle.net/10222/21432

Chicago Manual of Style (16^th Edition):

Toganassova, Dilyara. “SOURCE APPORTIONMENT OF PM2.5 SHIP EMISSIONS IN HALIFAX, NOVA SCOTIA, CANADA.” 2013. Masters Thesis, Dalhousie University. Accessed April 10, 2021. http://hdl.handle.net/10222/21432.

MLA Handbook (7^th Edition):

Toganassova, Dilyara. “SOURCE APPORTIONMENT OF PM2.5 SHIP EMISSIONS IN HALIFAX, NOVA SCOTIA, CANADA.” 2013. Web. 10 Apr 2021.

Vancouver:

Toganassova D. SOURCE APPORTIONMENT OF PM2.5 SHIP EMISSIONS IN HALIFAX, NOVA SCOTIA, CANADA. [Internet] [Masters thesis]. Dalhousie University; 2013. [cited 2021 Apr 10]. Available from: http://hdl.handle.net/10222/21432.

Council of Science Editors:

Toganassova D. SOURCE APPORTIONMENT OF PM2.5 SHIP EMISSIONS IN HALIFAX, NOVA SCOTIA, CANADA. [Masters Thesis]. Dalhousie University; 2013. Available from: http://hdl.handle.net/10222/21432

San Jose State University

23. Gulati, Avni. Social Recommendation Systems.

Degree: MS, Computer Engineering, 2018, San Jose State University

URL: https://doi.org/10.31979/etd.6z86-4w3x ; https://scholarworks.sjsu.edu/etd_theses/4968

► In recent years, with the rise of online social networks, personalized recommendations that leverage the aspect of social connections have become a very intriguing… (more)

Subjects/Keywords: influence propagation; matrix factorization; recommendation system; social network; social regularization

Record Details Similar Records Cite « Share

❌

APA · Chicago · MLA · Vancouver · CSE | Export to Zotero / EndNote / Reference Manager

APA (6^th Edition):

Gulati, A. (2018). Social Recommendation Systems. (Masters Thesis). San Jose State University. Retrieved from https://doi.org/10.31979/etd.6z86-4w3x ; https://scholarworks.sjsu.edu/etd_theses/4968

Chicago Manual of Style (16^th Edition):

Gulati, Avni. “Social Recommendation Systems.” 2018. Masters Thesis, San Jose State University. Accessed April 10, 2021. https://doi.org/10.31979/etd.6z86-4w3x ; https://scholarworks.sjsu.edu/etd_theses/4968.

MLA Handbook (7^th Edition):

Gulati, Avni. “Social Recommendation Systems.” 2018. Web. 10 Apr 2021.

Vancouver:

Gulati A. Social Recommendation Systems. [Internet] [Masters thesis]. San Jose State University; 2018. [cited 2021 Apr 10]. Available from: https://doi.org/10.31979/etd.6z86-4w3x ; https://scholarworks.sjsu.edu/etd_theses/4968.

Council of Science Editors:

Gulati A. Social Recommendation Systems. [Masters Thesis]. San Jose State University; 2018. Available from: https://doi.org/10.31979/etd.6z86-4w3x ; https://scholarworks.sjsu.edu/etd_theses/4968

University of Alberta

24. Liu, Bang. Matrix and Tensor Approximation for Internet Latency Prediction and Online Purchase Prediction.

Degree: MS, Department of Electrical and Computer Engineering, 2015, University of Alberta

URL: https://era.library.ualberta.ca/files/zw12z797h

► In this thesis, I study the application of matrix and tensor approximation techniques to Internet latency prediction and purchase prediction in e-commerce. Traditional approaches for… (more)

Subjects/Keywords: Network Latency Prediction; Online Purchase Prediction; Matrix Factorization

Record Details Similar Records Cite « Share

❌

APA · Chicago · MLA · Vancouver · CSE | Export to Zotero / EndNote / Reference Manager

APA (6^th Edition):

Liu, B. (2015). Matrix and Tensor Approximation for Internet Latency Prediction and Online Purchase Prediction. (Masters Thesis). University of Alberta. Retrieved from https://era.library.ualberta.ca/files/zw12z797h

Chicago Manual of Style (16^th Edition):

Liu, Bang. “Matrix and Tensor Approximation for Internet Latency Prediction and Online Purchase Prediction.” 2015. Masters Thesis, University of Alberta. Accessed April 10, 2021. https://era.library.ualberta.ca/files/zw12z797h.

MLA Handbook (7^th Edition):

Liu, Bang. “Matrix and Tensor Approximation for Internet Latency Prediction and Online Purchase Prediction.” 2015. Web. 10 Apr 2021.

Vancouver:

Liu B. Matrix and Tensor Approximation for Internet Latency Prediction and Online Purchase Prediction. [Internet] [Masters thesis]. University of Alberta; 2015. [cited 2021 Apr 10]. Available from: https://era.library.ualberta.ca/files/zw12z797h.

Council of Science Editors:

Liu B. Matrix and Tensor Approximation for Internet Latency Prediction and Online Purchase Prediction. [Masters Thesis]. University of Alberta; 2015. Available from: https://era.library.ualberta.ca/files/zw12z797h

NSYSU

25. Ku, Che-wen. Topic Recommendation and Discovery based on Matrix Factorization.

Degree: Master, Information Management, 2017, NSYSU

URL: http://etd.lib.nsysu.edu.tw/ETD-db/ETD-search/view_etd?URN=etd-0619117-145750

► Nowadays, there are more and more text documents on the Internet with the development of the Internet, because much information is related to text. Thus,… (more)

Subjects/Keywords: Non-negative Matrix Factorization; Topic Discovery; Recommendation; Topic Modeling

Record Details Similar Records Cite « Share

❌

APA · Chicago · MLA · Vancouver · CSE | Export to Zotero / EndNote / Reference Manager

APA (6^th Edition):

Ku, C. (2017). Topic Recommendation and Discovery based on Matrix Factorization. (Thesis). NSYSU. Retrieved from http://etd.lib.nsysu.edu.tw/ETD-db/ETD-search/view_etd?URN=etd-0619117-145750

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

Chicago Manual of Style (16^th Edition):

Ku, Che-wen. “Topic Recommendation and Discovery based on Matrix Factorization.” 2017. Thesis, NSYSU. Accessed April 10, 2021. http://etd.lib.nsysu.edu.tw/ETD-db/ETD-search/view_etd?URN=etd-0619117-145750.

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

MLA Handbook (7^th Edition):

Ku, Che-wen. “Topic Recommendation and Discovery based on Matrix Factorization.” 2017. Web. 10 Apr 2021.

Vancouver:

Ku C. Topic Recommendation and Discovery based on Matrix Factorization. [Internet] [Thesis]. NSYSU; 2017. [cited 2021 Apr 10]. Available from: http://etd.lib.nsysu.edu.tw/ETD-db/ETD-search/view_etd?URN=etd-0619117-145750.

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

Council of Science Editors:

Ku C. Topic Recommendation and Discovery based on Matrix Factorization. [Thesis]. NSYSU; 2017. Available from: http://etd.lib.nsysu.edu.tw/ETD-db/ETD-search/view_etd?URN=etd-0619117-145750

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

Purdue University

26. Kang, Jisun. Improving a mesh segmentation algorithm based on non-negative matrix factorization.

Degree: MS, Computer Graphics Technology, 2016, Purdue University

URL: https://docs.lib.purdue.edu/open_access_theses/861

► 3D Mesh segmentation is used in various applications such as object recognition, reconstruction, and analyzing structure of meshes. The method for 3D mesh segmentation… (more)

Subjects/Keywords: Applied sciences; Mesh segmentation; Non-negative matrix factorization; Computer Sciences

Record Details Similar Records Cite « Share

❌

APA · Chicago · MLA · Vancouver · CSE | Export to Zotero / EndNote / Reference Manager

APA (6^th Edition):

Kang, J. (2016). Improving a mesh segmentation algorithm based on non-negative matrix factorization. (Thesis). Purdue University. Retrieved from https://docs.lib.purdue.edu/open_access_theses/861

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

Chicago Manual of Style (16^th Edition):

Kang, Jisun. “Improving a mesh segmentation algorithm based on non-negative matrix factorization.” 2016. Thesis, Purdue University. Accessed April 10, 2021. https://docs.lib.purdue.edu/open_access_theses/861.

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

MLA Handbook (7^th Edition):

Kang, Jisun. “Improving a mesh segmentation algorithm based on non-negative matrix factorization.” 2016. Web. 10 Apr 2021.

Vancouver:

Kang J. Improving a mesh segmentation algorithm based on non-negative matrix factorization. [Internet] [Thesis]. Purdue University; 2016. [cited 2021 Apr 10]. Available from: https://docs.lib.purdue.edu/open_access_theses/861.

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

Council of Science Editors:

Kang J. Improving a mesh segmentation algorithm based on non-negative matrix factorization. [Thesis]. Purdue University; 2016. Available from: https://docs.lib.purdue.edu/open_access_theses/861

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

Universidade Nova

27. Dias, Pedro Ricardo Gomes. Recommending media content based on machine learning methods.

Degree: 2011, Universidade Nova

URL: http://www.rcaap.pt/detail.jsp?id=oai:run.unl.pt:10362/6581

►

Dissertação para obtenção do Grau de Mestre em Engenharia Informática

Information is nowadays made available and consumed faster than ever before. This information technology generation… (more)

Subjects/Keywords: Recommender systems; Collaborative filtering; Matrix factorization; Groupbased recommendations; Interactive TV

Record Details Similar Records Cite « Share

❌

APA · Chicago · MLA · Vancouver · CSE | Export to Zotero / EndNote / Reference Manager

APA (6^th Edition):

Dias, P. R. G. (2011). Recommending media content based on machine learning methods. (Thesis). Universidade Nova. Retrieved from http://www.rcaap.pt/detail.jsp?id=oai:run.unl.pt:10362/6581

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

Chicago Manual of Style (16^th Edition):

Dias, Pedro Ricardo Gomes. “Recommending media content based on machine learning methods.” 2011. Thesis, Universidade Nova. Accessed April 10, 2021. http://www.rcaap.pt/detail.jsp?id=oai:run.unl.pt:10362/6581.

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

MLA Handbook (7^th Edition):

Dias, Pedro Ricardo Gomes. “Recommending media content based on machine learning methods.” 2011. Web. 10 Apr 2021.

Vancouver:

Dias PRG. Recommending media content based on machine learning methods. [Internet] [Thesis]. Universidade Nova; 2011. [cited 2021 Apr 10]. Available from: http://www.rcaap.pt/detail.jsp?id=oai:run.unl.pt:10362/6581.

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

Council of Science Editors:

Dias PRG. Recommending media content based on machine learning methods. [Thesis]. Universidade Nova; 2011. Available from: http://www.rcaap.pt/detail.jsp?id=oai:run.unl.pt:10362/6581

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

28. Heß, Sibylle Charlotte. A mathematical theory of making hard decisions: model selection and robustness of matrix factorization with binary constraints.

Degree: 2018, Technische Universität Dortmund

URL: http://dx.doi.org/10.17877/DE290R-20240

► One of the first and most fundamental tasks in machine learning is to group observations within a dataset. Given a notion of similarity, finding those… (more)

▼ One of the first and most fundamental tasks in machine learning is to group observations within a dataset. Given a notion of similarity, finding those instances which are outstandingly similar to each other has manifold applications. Recommender systems and topic analysis in text data are examples which are most intuitive to grasp. The interpretation of the groups, called clusters, is facilitated if the assignment of samples is definite. Especially in high-dimensional data, denoting a degree to which an observation belongs to a specified cluster requires a subsequent processing of the model to filter the most important information. We argue that a good summary of the data provides hard decisions on the following question: how many groups are there, and which observations belong to which clusters? In this work, we contribute to the theoretical and practical background of clustering tasks, addressing one or both aspects of this question. Our overview of state-of-the-art clustering approaches details the challenges of our ambition to provide hard decisions. Based on this overview, we develop new methodologies for two branches of clustering: the one concerns the derivation of nonconvex clusters, known as spectral clustering; the other addresses the identification of biclusters, a set of samples together with similarity defining features, via Boolean matrix factorization. One of the main challenges in both considered settings is the robustness to noise. Assuming that the issue of robustness is controllable by means of theoretical insights, we have a closer look at those aspects of established clustering methods which lack a theoretical foundation. In the scope of Boolean matrix factorization, we propose a versatile framework for the optimization of matrix factorizations subject to binary constraints. Especially Boolean factorizations have been computed by intuitive methods so far, implementing greedy heuristics which lack quality guarantees of obtained solutions. In contrast, we propose to build upon recent advances in nonconvex optimization theory. This enables us to provide convergence guarantees to local optima of a relaxed objective, requiring only approximately binary factor matrices. By means of this new optimization scheme PAL-Tiling, we propose two approaches to automatically determine the number of clusters. The one is based on information theory, employing the minimum description length principle, and the other is a novel statistical approach, controlling the false discovery rate. The flexibility of our framework PAL-Tiling enables the optimization of novel factorization schemes. In a different context, where every data point belongs to a pre-defined class, a characterization of the classes may be obtained by Boolean factorizations. However, there are cases where this traditional factorization scheme is not sufficient. Therefore, we propose the integration of another factor matrix, reflecting class-specific differences within a cluster. Our theoretical considerations are complemented by empirical… Advisors/Committee Members: Morik, Katharina (advisor), Siebes, Arno P. J. M. (referee).

Subjects/Keywords: Matrix factorization; Binary optimization; Clustering; 004; Matrizenzerlegung; Boolesche Optimierung; Cluster-Analyse

Record Details Similar Records Cite « Share

❌

APA · Chicago · MLA · Vancouver · CSE | Export to Zotero / EndNote / Reference Manager

APA (6^th Edition):

Heß, S. C. (2018). A mathematical theory of making hard decisions: model selection and robustness of matrix factorization with binary constraints. (Doctoral Dissertation). Technische Universität Dortmund. Retrieved from http://dx.doi.org/10.17877/DE290R-20240

Chicago Manual of Style (16^th Edition):

Heß, Sibylle Charlotte. “A mathematical theory of making hard decisions: model selection and robustness of matrix factorization with binary constraints.” 2018. Doctoral Dissertation, Technische Universität Dortmund. Accessed April 10, 2021. http://dx.doi.org/10.17877/DE290R-20240.

MLA Handbook (7^th Edition):

Heß, Sibylle Charlotte. “A mathematical theory of making hard decisions: model selection and robustness of matrix factorization with binary constraints.” 2018. Web. 10 Apr 2021.

Vancouver:

Heß SC. A mathematical theory of making hard decisions: model selection and robustness of matrix factorization with binary constraints. [Internet] [Doctoral dissertation]. Technische Universität Dortmund; 2018. [cited 2021 Apr 10]. Available from: http://dx.doi.org/10.17877/DE290R-20240.

Council of Science Editors:

Heß SC. A mathematical theory of making hard decisions: model selection and robustness of matrix factorization with binary constraints. [Doctoral Dissertation]. Technische Universität Dortmund; 2018. Available from: http://dx.doi.org/10.17877/DE290R-20240

University of Ontario Institute of Technology

29. Shanks, Ryan A. Towards parallax-based unencumbered displays.

Degree: 2015, University of Ontario Institute of Technology

URL: http://hdl.handle.net/10155/620

► We present an analysis of content adaptive parallax barriers used for multi-layer unencumbered displays. We explain the techniques involved in detail from the input light… (more)

Subjects/Keywords: Computational displays; Content adaptive parallax barriers; Non-negative matrix factorization; Autostereoscopic

Record Details Similar Records Cite « Share

❌

APA · Chicago · MLA · Vancouver · CSE | Export to Zotero / EndNote / Reference Manager

APA (6^th Edition):

Shanks, R. A. (2015). Towards parallax-based unencumbered displays. (Thesis). University of Ontario Institute of Technology. Retrieved from http://hdl.handle.net/10155/620

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

Chicago Manual of Style (16^th Edition):

Shanks, Ryan A. “Towards parallax-based unencumbered displays.” 2015. Thesis, University of Ontario Institute of Technology. Accessed April 10, 2021. http://hdl.handle.net/10155/620.

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

MLA Handbook (7^th Edition):

Shanks, Ryan A. “Towards parallax-based unencumbered displays.” 2015. Web. 10 Apr 2021.

Vancouver:

Shanks RA. Towards parallax-based unencumbered displays. [Internet] [Thesis]. University of Ontario Institute of Technology; 2015. [cited 2021 Apr 10]. Available from: http://hdl.handle.net/10155/620.

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

Council of Science Editors:

Shanks RA. Towards parallax-based unencumbered displays. [Thesis]. University of Ontario Institute of Technology; 2015. Available from: http://hdl.handle.net/10155/620

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

University of Ottawa

30. Agagu, Tosin. Recommendation Approaches Using Context-Aware Coupled Matrix Factorization .

Degree: 2017, University of Ottawa

URL: http://hdl.handle.net/10393/37012

► In general, recommender systems attempt to estimate user preference based on historical data. A context-aware recommender system attempts to generate better recommendations using contextual information.… (more)

Subjects/Keywords: Context-aware recommender system; Coupled matrix factorization; Recommendations; Context

Record Details Similar Records Cite « Share

❌

APA · Chicago · MLA · Vancouver · CSE | Export to Zotero / EndNote / Reference Manager

APA (6^th Edition):

Agagu, T. (2017). Recommendation Approaches Using Context-Aware Coupled Matrix Factorization . (Thesis). University of Ottawa. Retrieved from http://hdl.handle.net/10393/37012

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

Chicago Manual of Style (16^th Edition):

Agagu, Tosin. “Recommendation Approaches Using Context-Aware Coupled Matrix Factorization .” 2017. Thesis, University of Ottawa. Accessed April 10, 2021. http://hdl.handle.net/10393/37012.

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

MLA Handbook (7^th Edition):

Agagu, Tosin. “Recommendation Approaches Using Context-Aware Coupled Matrix Factorization .” 2017. Web. 10 Apr 2021.

Vancouver:

Agagu T. Recommendation Approaches Using Context-Aware Coupled Matrix Factorization . [Internet] [Thesis]. University of Ottawa; 2017. [cited 2021 Apr 10]. Available from: http://hdl.handle.net/10393/37012.

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

Council of Science Editors:

Agagu T. Recommendation Approaches Using Context-Aware Coupled Matrix Factorization . [Thesis]. University of Ottawa; 2017. Available from: http://hdl.handle.net/10393/37012

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

		in
And / Or
		in
And / Or
		in
And / Or
		in

Open Access Theses and Dissertations