Empirical canonical correlation analysis in subspaces
2004 (English)In: Conference Record of the Thirty-Eighth Asilomar Conference on Signals, Systems and Computers, IEEE Communications Society, 2004, Vol. 1, 994-997 p.Conference paper (Refereed)
This paper addresses canonical correlation analysis of two-channel data, when channel covariances are estimated from a limited number of samples, and are not necessarily full-rank. We show that empirical canonical correlations measure the cosines of the principal angles between the row spaces of the data matrices for the two channels. When the number of samples is smaller than the sum of the ranks of the two data matrices, some of the empirical canonical correlations become one, regardless of the two-channel model that generates the samples. In such cases, the empirical canonical correlations may not be used as estimates of correlation between random variables.
Place, publisher, year, edition, pages
IEEE Communications Society, 2004. Vol. 1, 994-997 p.
Research subject Signal Processing
IdentifiersURN: urn:nbn:se:ltu:diva-35184DOI: 10.1109/ACSSC.2004.1399288Local ID: 99a96f70-f25e-11df-8b36-000ea68e967bISBN: 0-7803-8622-1 (print)OAI: oai:DiVA.org:ltu-35184DiVA: diva2:1008436
Asilomar Conference on Signals, Systems and Computers : 07/11/2004 - 10/11/2004
Upprättat; 2004; 20101117 (ysko)2016-09-302016-09-30Bibliographically approved