资源分类
》 资源 》论文》Global Optimality of Local Search for Low Rank Matrix Recovery

Global Optimality of Local Search for Low Rank Matrix Recovery

2020-02-05 | |  66 |   35 |   0

Abstract 

We show that there are no spurious local minima in the non-convex factorized parametrization of low-rank matrix recovery from incoherent linear measurements. With noisy measurements we show all local minima are very close to a global optimum. Together with a curvature bound at saddle points, this yields a polynomial time global convergence guarantee for stochastic gradient descent from random initialization.

上一篇：Near-Optimal Smoothing of Structured Conditional Probability Matrices

下一篇：Using Social Dynamics to Make Individual Predictions: Variational Inference with a Stochastic Kinetic Model

用户评价
全部评价

热门资源

  • The Variational S...

    Unlike traditional images which do not offer in...

  • Learning to Predi...

    Much of model-based reinforcement learning invo...

  • Stratified Strate...

    In this paper we introduce Stratified Strategy ...

  • A Mathematical Mo...

    Direct democracy, where each voter casts one vo...

  • Rating-Boosted La...

    The performance of a recommendation system reli...