Revisiting maximal response-based local identification of overcomplete dictionaries

Zahra Shakeri, Waheed U. Bajwa

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

This paper revisits the problem of recovery of an overcomplete dictionary in a local neighborhood from training samples using the so-called maximal response criterion (MRC). While it is known in the literature that MRC can be used for asymptotic exact recovery of a dictionary in a local neighborhood, those results do not allow for linear (in the ambient dimension) scaling of sparsity levels in signal representations. In this paper, a new proof technique is leveraged to establish that MRC can in fact handle linear sparsity (modulo a logarithmic factor) of signal representations. While the focus of this work is on asymptotic exact recovery, the same ideas can be used in a straightforward manner to strengthen the original MRC-based results involving noisy observations and finite number of training samples.

Original languageEnglish (US)
Title of host publication2016 IEEE Sensor Array and Multichannel Signal Processing Workshop, SAM 2016
PublisherIEEE Computer Society
ISBN (Electronic)9781509021031
DOIs
StatePublished - Sep 15 2016
Event2016 IEEE Sensor Array and Multichannel Signal Processing Workshop, SAM 2016 - Rio de Rio de Janeiro, Brazil
Duration: Jul 10 2016Jul 13 2016

Publication series

NameProceedings of the IEEE Sensor Array and Multichannel Signal Processing Workshop
Volume2016-September
ISSN (Electronic)2151-870X

Other

Other2016 IEEE Sensor Array and Multichannel Signal Processing Workshop, SAM 2016
CountryBrazil
CityRio de Rio de Janeiro
Period7/10/167/13/16

All Science Journal Classification (ASJC) codes

  • Signal Processing
  • Control and Systems Engineering
  • Electrical and Electronic Engineering

Fingerprint Dive into the research topics of 'Revisiting maximal response-based local identification of overcomplete dictionaries'. Together they form a unique fingerprint.

Cite this