Linear Convergence of Frank-Wolfe for Rank-One Matrix Recovery Without Strong Convexity
This provides a faster algorithm for problems like phase retrieval and robust PCA, but it is incremental as it builds on existing Frank-Wolfe methods with a new condition for convergence.
The paper tackles the problem of low-rank matrix recovery by establishing a condition under which convex relaxations yield unique rank-one solutions, and shows that the Frank-Wolfe method with line-search achieves linear convergence to an ε-approximated solution in O(log(1/ε)) iterations, improving from the previous O(1/ε) bound, without requiring strong convexity.
We consider convex optimization problems which are widely used as convex relaxations for low-rank matrix recovery problems. In particular, in several important problems, such as phase retrieval and robust PCA, the underlying assumption in many cases is that the optimal solution is rank-one. In this paper we consider a simple and natural sufficient condition on the objective so that the optimal solution to these relaxations is indeed unique and rank-one. Mainly, we show that under this condition, the standard Frank-Wolfe method with line-search (i.e., without any tuning of parameters whatsoever), which only requires a single rank-one SVD computation per iteration, finds an $ε$-approximated solution in only $O(\log{1/ε})$ iterations (as opposed to the previous best known bound of $O(1/ε)$), despite the fact that the objective is not strongly convex. We consider several variants of the basic method with improved complexities, as well as an extension motivated by robust PCA, and finally, an extension to nonsmooth problems.