Approximate inference in credal networks by variational mean field methods

Jaime Shinsuke Ide, Fabio Gagliardi Cozman

Research output: Contribution to conferenceConference Paper

7 Scopus citations

Abstract

© 2005 Society for Imprecise Probability: Theories and Applications, SIPTA. All rights reserved. Graph-theoretical representations for sets of probability measures (credal networks) generally display high complexity, and approximate inference seems to be a natural solution for large networks. This paper introduces a variational approach to approximate inference in credal networks: we show how to formulate mean field approximations using naive (fully factorized) and structured (tree-like) schemes. We discuss the computational advantages of the variational approach, and present examples that illustrate the mechanics of the proposal.
Original languageAmerican English
StatePublished - 1 Jan 2005
Externally publishedYes
Event4th International Symposium on Imprecise Probabilities and Their Applications, ISIPTA 2005 -
Duration: 1 Jan 2005 → …

Conference

Conference4th International Symposium on Imprecise Probabilities and Their Applications, ISIPTA 2005
Period1/01/05 → …

Fingerprint

Dive into the research topics of 'Approximate inference in credal networks by variational mean field methods'. Together they form a unique fingerprint.

Cite this