Non-Convex Matrix Completion Against a Semi-Random Adversary

COLT, pp. 1362-1394, 2018.

Cited by: 5|Bibtex|Views8|Links
EI

Abstract:

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

Code:

Data:

Your rating :
0

 

Tags
Comments