Optimal Spectral Shrinkage and PCA with Heteroscedastic Noise

Tuesday, March 19, 2019 - 2:00pm
Math Sci 111
Will Leeb
(University of Minnesota)

I will discuss recent work on the related problems of denoising, covariance estimation, and principal component analysis for the spiked covariance model with heteroscedastic noise. Specifically, I will present an estimator of the principal components based on whitening the noise, and optimal singular value and eigenvalue shrinkers for use with these estimated principal components. I will also show new results on the optimality of whitening for principal subspace estimation. This is joint work with Elad Romanov of the Hebrew University.

Event Type: