Taxonomy of Dual Block-Coordinate Ascent Methods for Discrete Energy Minimization

TitleTaxonomy of Dual Block-Coordinate Ascent Methods for Discrete Energy Minimization
Publication TypeConference Paper
Year of Publication2020
AuthorsTourani, S, Shekhovtsov, A, Rother, C, Savchynskyy, B
Conference NameAISTATS 2020
Abstract

We consider the maximum-a-posteriori inference problem in discrete graphical models and study solvers based on the dual block-coordinate ascent rule. We map all existing solvers in a single framework, allowing for a better understanding of their design principles. We theoretically show that some block-optimizing updates are sub-optimal and how to strictly improve them. On a wide range of problem instances of varying graph connec-tivity, we study the performance of existing solvers as well as new variants that can be obtained within the framework. As a result of this exploration we build a new state-of-the art solver, performing uniformly better on the whole range of test instances.

URLhttps://gitlab.com/
Citation KeyTourani2020