Noisy matrix decomposition via convex relaxation: Optimal rates in high dimensions

Details Noisy matrix decomposition via convex relaxation: Optimal rates in high dimensions Noisy matrix decomposition via convex relaxation: Optimal rates in high dimensions

2011-02-23

arxiv.org/abs/1102.4807v3

Statistics

Machine Learning

41 pages, 2 figures

Scientific paper

We analyze a class of estimators based on convex relaxation for solving high-dimensional matrix decomposition problems. The observations are noisy realizations of a linear transformation $\mathfrak{X}$ of the sum of an approximately) low rank matrix $\Theta^\star$ with a second matrix $\Gamma^\star$ endowed with a complementary form of low-dimensional structure; this set-up includes many statistical models of interest, including factor analysis, multi-task regression, and robust covariance estimation. We derive a general theorem that bounds the Frobenius norm error for an estimate of the pair $(\Theta^\star, \Gamma^\star)$ obtained by solving a convex optimization problem that combines the nuclear norm with a general decomposable regularizer. Our results utilize a "spikiness" condition that is related to but milder than singular vector incoherence. We specialize our general result to two cases that have been studied in past work: low rank plus an entrywise sparse matrix, and low rank plus a columnwise sparse matrix. For both models, our theory yields non-asymptotic Frobenius error bounds for both deterministic and stochastic noise matrices, and applies to matrices $\Theta^\star$ that can be exactly or approximately low rank, and matrices $\Gamma^\star$ that can be exactly or approximately sparse. Moreover, for the case of stochastic noise matrices and the identity observation operator, we establish matching lower bounds on the minimax error. The sharpness of our predictions is confirmed by numerical simulations.

Affiliated with

Also associated with

No associations

Rating

Noisy matrix decomposition via convex relaxation: Optimal rates in high dimensions does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.

If you have personal experience with Noisy matrix decomposition via convex relaxation: Optimal rates in high dimensions, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Noisy matrix decomposition via convex relaxation: Optimal rates in high dimensions will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFWR-SCP-O-175348