Events Calendar

MS Final Exam – Cheng Gao

Large scale tensor decomposition algorithm using block-randomized stochastic proximal gradient

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. In the latest decades, people tend to deal with these problems leverage data sparsity. There are many challenge for people to resolve by applying data sparsity such as high memory cost and computational flops. Inspired by stochastic optimization's low memory consuming and per iteration complexity, we proposed our stochastic optimization framework 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. One more insight for our algorithm is that it could handle many frequently used regularizers and constraints which is more flexible compared to many existing algorithms. Applications to Hyper Spectrum Images are considered in the experiment part.

Major Advisor: Xiao Fu
Committee: Jinsub Kim
Committee: Fuxin Li
GCR: Yelda Turkan

Friday, May 31 at 3:00pm to 5:00pm

Kelley Engineering Center, 1007
110 SW Park Terrace, Corvallis, OR 97331

Event Type

Lecture or Presentation

Event Topic

Research

Organization
Electrical Engineering and Computer Science
Contact Name

Calvin Hughes

Contact Email

calvin.hughes@oregonstate.edu

Subscribe
Google Calendar iCal Outlook

Recent Activity