NIPS Proceedingsβ

Implicit Regularization in Matrix Factorization

Part of: Advances in Neural Information Processing Systems 30 (NIPS 2017)

[PDF] [BibTeX] [Supplemental] [Reviews]


Conference Event Type: Poster


We study implicit regularization when optimizing an underdetermined quadratic objective over a matrix $X$ with gradient descent on a factorization of X. We conjecture and provide empirical and theoretical evidence that with small enough step sizes and initialization close enough to the origin, gradient descent on a full dimensional factorization converges to the minimum nuclear norm solution.