Theoretical properties for neural networks with weight matrices of low displacement rank

Liang Zhao, Siyu Liao, Yanzhi Wang, Zhe Li, Jian Tang, Victor Pan, Bo Yuan

Research output: Contribution to journalArticlepeer-review

Abstract

Recently low displacement rank (LDR) matrices, or so-called structured matrices, have been proposed to compress large-scale neural networks. Empirical results have shown that neural networks with weight matrices of LDR matrices, referred as LDR neural networks, can achieve significant reduction in space and computational complexity while retaining high accuracy. We formally study LDR matrices in deep learning. First, we prove the universal approximation property of LDR neural networks with a mild condition on the displacement operators. We then show that the error bounds of LDR neural networks are as efficient as general neural networks with both single-layer and multiple-layer structure. Finally, we propose back-propagation based training algorithm for general LDR neural networks.

Original languageEnglish (US)
JournalUnknown Journal
StatePublished - Mar 1 2017

Keywords

  • Deep learning
  • Matrix displacement
  • Structured matrices

ASJC Scopus subject areas

  • General

Fingerprint Dive into the research topics of 'Theoretical properties for neural networks with weight matrices of low displacement rank'. Together they form a unique fingerprint.

Cite this