LOW-RANK TENSOR DECOMPOSITION WITH DEEP NETWORK PRIORS

Abstract

In this project, the PI will develop and study a new approach to low-rank matrix-tensor decomposition that is robust to a wide class of signal and noise models. The PI calls the general approach DeepTensor. A core enabling observation is that deep generative networks produce signals that are implicitly regularized due to the networks’ inherent inductive bias; thus the hope is to obtain improved correctness and efficiency.

Document Details

Document Type
DoD Grant Award
Publication Date
Mar 07, 2023
Source ID
FA95502210060

Entities

People

  • Richard G. Baraniuk

Organizations

  • Air Force Office of Scientific Research
  • Rice University
  • United States Air Force

Tags

Fields of Study

  • Computer science

Readers

  • Neural Network Machine Learning.