Relative Interior Rule in Block-Coordinate Descent

CVPR 2020

Relative Interior Rule in Block-Coordinate Descent

Sep 29, 2020
|
28 views
Details
Authors: Tomáš Werner, Daniel Průša, Tomáš Dlask Description: It is well-known that for general convex optimization problems, block-coordinate descent can get stuck in poor local optima. Despite that, versions of this method known as convergent message passing are very successful to approximately solve the dual LP relaxation of the MAP inference problem in graphical models. In attempt to identify the reason why these methods often achieve good local minima, we argue that if in block-coordinate descent the set of minimizers over a variable block has multiple elements, one should choose an element from the relative interior of this set. We show that this rule is not worse than any other rule for choosing block-minimizers. Based on this observation, we develop a theoretical framework for block-coordinate descent applied to general convex problems. We illustrate this theory on convergent message-passing methods.

Comments
loading...