Tensor Learning Team Seminar (Talk by Osman Asif Malik, University of Colorado Boulder)

Speaker: Osman Asif Malik, PhD Candidate in Applied Mathematics, University of Colorado Boulder
Title: A Sampling-Based Method for Tensor Ring Decomposition
Abstract: In this talk, we propose a sampling-based method for computing the tensor ring (TR) decomposition of a data tensor. The method uses leverage score sampled alternating least squares to fit the TR cores in an iterative fashion. By taking advantage of the special structure of TR tensors, we can efficiently estimate the leverage scores and attain a method which has complexity sublinear in the number of input tensor entries. We provide high-probability relative-error guarantees for the sampled least squares problems. We will also show some results from decomposition and feature extraction experiments.

For further details, please see our preprint at https://arxiv.org/abs/2010.08581