Analysis of fast structured dictionary learning

Abstract

Sparsity-based models and techniques have been exploited in many signal processing and imaging applications. Data-driven methods based on dictionary and sparsifying transform learning enable learning rich image features from data and can outperform analytical models. In particular, alternating optimization algorithms have been popular for learning such models. In this work, we focus on alternating minimization for a specific structured unitary sparsifying operator learning problem and provide a convergence analysis. While the algorithm converges to the critical points of the problem generally, our analysis establishes under mild assumptions, the local linear convergence of the algorithm to the underlying sparsifying model of the data. Analysis and numerical simulations show that our assumptions hold for standard probabilistic data models. In practice, the algorithm is robust to initialization.

Document Details

Document Type
Pub Defense Publication
Publication Date
Nov 19, 2019
Source ID
10.1093/imaiai/iaz028

Entities

People

  • Anna Ma
  • Deanna Needell
  • Saiprasad Ravishankar

Organizations

  • Army Research Office
  • Claremont Graduate University
  • Defense Advanced Research Projects Agency
  • Michigan State University
  • National Institutes of Health
  • National Science Foundation
  • Office of Naval Research
  • University of California, Los Angeles
  • University of Illinois Urbana–Champaign

Tags

Fields of Study

  • Computer science

Readers

  • Brain and Cognitive Science; Experimental Psychology; Cognitive Neuroscience
  • Computational Modeling and Simulation
  • Neural Network Machine Learning.