Fast Algorithms for Robust PCA via Gradient Descent
share
We consider the problem of Robust PCA in the fully and partially observed settings. Without corruptions, this is the well-known matrix completion problem. From a statistical standpoint this problem has been recently well-studied, and conditions on when recovery is possible (how many observations do we need, how many corruptions can we tolerate) via polynomial-time algorithms is by now understood. This paper presents and analyzes a non-convex optimization approach that greatly reduces the computational complexity of the above problems, compared to the best available algorithms. In particular, in the fully observed case, with r denoting rank and d dimension, we reduce the complexity from O(r^2d^2(1/ε)) to O(rd^2(1/ε)) -- a big savings when the rank is big. For the partially observed case, we show the complexity of our algorithm is no more than O(r^4d d (1/ε)). Not only is this the best-known run-time for a provable algorithm under partial observation, but in the setting where r is small compared to d, it also allows for near-linear-in-d run-time that can be exploited in the fully-observed case as well, by simply running our algorithm on a subset of the observations.
READ FULL TEXT