Provable Efficient Online Matrix Completion via Non-convex Stochastic Gradient Descent
This addresses the inefficiency of existing algorithms in online settings for applications requiring dynamic updates, though it is incremental as it adapts known methods to a new setting.
The paper tackles the problem of online matrix completion, where entries are observed sequentially, by proposing a provable and efficient algorithm based on non-convex stochastic gradient descent. The result achieves near-linear total runtime and competitive sample complexity compared to state-of-the-art offline methods.
Matrix completion, where we wish to recover a low rank matrix by observing a few entries from it, is a widely studied problem in both theory and practice with wide applications. Most of the provable algorithms so far on this problem have been restricted to the offline setting where they provide an estimate of the unknown matrix using all observations simultaneously. However, in many applications, the online version, where we observe one entry at a time and dynamically update our estimate, is more appealing. While existing algorithms are efficient for the offline setting, they could be highly inefficient for the online setting. In this paper, we propose the first provable, efficient online algorithm for matrix completion. Our algorithm starts from an initial estimate of the matrix and then performs non-convex stochastic gradient descent (SGD). After every observation, it performs a fast update involving only one row of two tall matrices, giving near linear total runtime. Our algorithm can be naturally used in the offline setting as well, where it gives competitive sample complexity and runtime to state of the art algorithms. Our proofs introduce a general framework to show that SGD updates tend to stay away from saddle surfaces and could be of broader interests for other non-convex problems to prove tight rates.