Learning mixtures of separable dictionaries for tensor data: Analysis and algorithms

Mohsen Ghassemi, Zahra Shakeri, Anand D. Sarwate, Waheed U. Bajwa

Research output: Contribution to journalArticlepeer-review

1 Scopus citations

Abstract

This work addresses the problem of learning sparse representations of tensor data using structured dictionary learning. It proposes learning a mixture of separable dictionaries to better capture the structure of tensor data by generalizing the separable dictionary learning model. Two different approaches for learning mixture of separable dictionaries are explored and sufficient conditions for local identifiability of the underlying dictionary are derived in each case. Moreover, computational algorithms are developed to solve the problem of learning mixture of separable dictionaries in both batch and online settings. Numerical experiments are used to show the usefulness of the proposed model and the efficacy of the developed algorithms.

Original languageEnglish (US)
Article number8892653
Pages (from-to)33-48
Number of pages16
JournalIEEE Transactions on Signal Processing
Volume68
DOIs
StatePublished - 2020

All Science Journal Classification (ASJC) codes

  • Signal Processing
  • Electrical and Electronic Engineering

Keywords

  • Dictionary learning
  • Kronecker structure
  • sample complexity
  • separation rank
  • tensor rearrangement

Fingerprint

Dive into the research topics of 'Learning mixtures of separable dictionaries for tensor data: Analysis and algorithms'. Together they form a unique fingerprint.

Cite this