Inference of principal components of noisy correlation matrices with prior information

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

Abstract

The problem of infering the top component of a noisy sample covariance matrix with prior information about the distribution of its entries is considered, in the framework of the spiked covariance model. Using the replica method of statistical physics the computation of the overlap between the top components of the sample and population covariance matrices is formulated as an explicit optimization problem for any kind of entry-wise prior information. The approach is illustrated on the case of top components including large entries, and the corresponding phase diagram is shown. The calculation predicts that the maximal sampling noise level at which the recovery of the top population component remains possible is higher than its counterpart in the spiked covariance model with no prior information.

Original languageEnglish
Title of host publicationConference Record of the 50th Asilomar Conference on Signals, Systems and Computers, ACSSC 2016
EditorsMichael B. Matthews
PublisherIEEE Computer Society
Pages95-99
Number of pages5
ISBN (Electronic)9781538639542
DOIs
Publication statusPublished - 1 Mar 2017
Event50th Asilomar Conference on Signals, Systems and Computers, ACSSC 2016 - Pacific Grove, United States
Duration: 6 Nov 20169 Nov 2016

Publication series

NameConference Record - Asilomar Conference on Signals, Systems and Computers
ISSN (Print)1058-6393

Conference

Conference50th Asilomar Conference on Signals, Systems and Computers, ACSSC 2016
Country/TerritoryUnited States
CityPacific Grove
Period6/11/169/11/16

Keywords

  • Phase Transitions
  • Prior Information
  • Random Matrix Theory
  • Replica Method
  • Spiked Covariance Model

Fingerprint

Dive into the research topics of 'Inference of principal components of noisy correlation matrices with prior information'. Together they form a unique fingerprint.

Cite this