Large Scale Tensor Decomposition Algorithms Using Block-randomized Stochastic Proximal Gradient

Graduate Thesis Or Dissertation

Público Deposited

Citeable URL: https://ir.library.oregonstate.edu/concern/graduate_thesis_or_dissertations/37720j83n

Descriptions

Attribute Name	Values
Creator	Gao, Cheng
Abstract	We consider the problem of computing the cannonical polyadic decomposition (CPD) for large-scale dense tensors. This work is a combination of alternating least squares and fiber sampling. Data sparsity can be leveraged to handle large tensor CPD, but this route is not feasible for dense data. Inspired by stochastic optimization's low memory consuming and per iteration complexity, we propose a stochastic optimization framework for CPD which combines the insights of block coordinate descent and stochastic proximal gradient. At the same time, we also provide an analysis for the convergence property which are unclear to many state-of-art. In addition, our algorithm can handle many frequently used regularizers and constraints, and thus is more flexible compared to many existing algorithms. Applications to hyperspectral images are considered in the experiment analysis part.
License	All rights reserved
Resource Type	Masters Thesis
Fecha de Emisión	2019-05-31
Degree Level	Master's
Degree Name	Master of Science (M.S.)
Degree Field	Electrical and Computer Engineering
Degree Grantor	Oregon State University
Commencement Year	2019
Advisor	Fu, Xiao
Committee Member	Li, Fuxin Kim, Jinsub Turkan, Yelda
Academic Affiliation	Electrical Engineering and Computer Science
Declaración de derechos	In Copyright
Related Items	Research group website
Publisher	Oregon State University
Peer Reviewed	No
Language	English [eng]

Parents:

This work has no parents.

En Collection:

Miniatura	Título	Fecha de subida	Visibilidad	Acciones
	GaoCheng2018.pdf	2019-06-13	Público	Descargar