Anytime marginal MAP inference

Denis Deratani Mauá, C.P. de Campos

Research output: Chapter in Book/Report/Conference proceedingChapterAcademicpeer-review

Abstract

This paper presents a new anytime algorithm for the marginal MAP problem in graphical models of bounded treewidth. We show asymptotic convergence and theoretical error bounds for any fixed step. Experiments show that it compares well to a state-of-the-art systematic search algorithm.
Original languageEnglish
Title of host publicationInternational Conference on Machine Learning (ICML)
PublisherOmnipress
Pages1471-1478
Number of pages8
Publication statusPublished - 2012
Externally publishedYes
Event29th International Conference on Machine Learning, ICML 2012 - Edinburgh, United Kingdom
Duration: 26 Jun 20121 Jul 2012

Conference

Conference29th International Conference on Machine Learning, ICML 2012
CountryUnited Kingdom
CityEdinburgh
Period26/06/121/07/12

Bibliographical note

(oral presentation, double-blind peer reviewed by >3 reviewers)

Fingerprint

Dive into the research topics of 'Anytime marginal MAP inference'. Together they form a unique fingerprint.

Cite this