Recovery of High-Dimensional Low-Rank Matrices

Stochastics Seminar
Thursday, November 12, 2015 - 15:05
1 hour (actually 50 minutes)
Skiles 006
Wharton School, University of Pennsylvania
Low-rank structure commonly arises in many applications including genomics, signal processing, and portfolio allocation. It is also used in many statistical inference methodologies such as principal component analysis. In this talk, I will present some recent results on recovery of a high-dimensional low-rank matrix with rank-one measurements and related problems including phase retrieval and optimal estimation of a spiked covariance matrix based on one-dimensional projections. I will also discuss structured matrix completion which aims to recover a low rank matrix based on incomplete, but structured observations.