How well do local algorithms solve semidefinite programs?

Abstract

Several probabilistic models from high-dimensional statistics and machine learning reveal an intriguing and yet poorly understood dichotomy. Either simple local algorithms succeed in estimating the object of interest, or even sophisticated semi-definite programming (SDP) relaxations fail. In order to explore this phenomenon, we study a classical SDP… (More)
DOI: 10.1145/3055399.3055451

Topics

1 Figure or Table

Slides referencing similar topics