Non-Convex Matrix Completion Against a Semi-Random Adversary
COLT, pp. 1362-1394, 2018.
Matrix completion is a well-studied problem with many machine learning applications. practice, the problem is often solved by non-convex optimization algorithms. However, the current theoretical analysis for non-convex algorithms relies heavily on the assumption that every entry is observed with exactly the same probability (p), which is...More
PPT (Upload PPT)