Spring 2015

Low-Rank Matrix Recovery Through Rank-One Projections

Monday, Mar. 16, 2015 9:50 am10:15 am PDT

Add to Calendar


Calvin Lab Auditorium

Estimation of low-rank matrices is of significant interest in a range of contemporary applications. In this talk we introduce a rank-one projection model for low-rank matrix recovery and propose a constrained nuclear norm minimization method for stable recovery of low-rank matrices in the noisy case. The procedure is adaptive to the rank and robust against small perturbations. The proposed estimator is shown to be rate-optimal under certain conditions. Applications to phase retrieval and estimation of spiked covariance matrices will also be discussed.