Learning compressed sensing

Yair Weiss, Hyun Sung Chang, William T. Freeman

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

28 Scopus citations

Abstract

Compressed sensing [7], [6] is a recent set of mathematical results showing that sparse signals can be exactly reconstructed from a small number of linear measurements. Interestingly, for ideal sparse signals with no measurement noise, random measurements allow perfect reconstruction while measurements based on principal component analysis (PCA) or independent component analysis (ICA) do not At the same time, for other signal and noise distributions, PCA and ICA can significantly outperform random projections in terms of enabling reconstruction from a small number of measurements. In this paper we ask: given a training set typical of the signals we wish to measure, what are the optimal set of linear projections for compressed sensing ? We show that the optimal projections are in general not the principal components nor the independent components of the data, but rather a seemingly novel set of projections that capture what is still uncertain about the signal, given the training set. We also show that the projections onto the learned uncertain components may far outperform random projections. This is particularly true in the case of natural images, where random projections have vanishingly small signal to noise ratio as the number of pixels becomes large.

Original languageAmerican English
Title of host publication45th Annual Allerton Conference on Communication, Control, and Computing 2007
PublisherUniversity of Illinois at Urbana-Champaign, Coordinated Science Laboratory and Department of Computer and Electrical Engineering
Pages535-541
Number of pages7
ISBN (Electronic)9781605600864
StatePublished - 2007
Event45th Annual Allerton Conference on Communication, Control, and Computing 2007 - Monticello, United States
Duration: 26 Sep 200728 Sep 2007

Publication series

Name45th Annual Allerton Conference on Communication, Control, and Computing 2007
Volume1

Conference

Conference45th Annual Allerton Conference on Communication, Control, and Computing 2007
Country/TerritoryUnited States
CityMonticello
Period26/09/0728/09/07

Fingerprint

Dive into the research topics of 'Learning compressed sensing'. Together they form a unique fingerprint.

Cite this