HELM: Highly efficient learning of mixed copula networks

Yaniv Tenzer, Gal Elidan

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

Learning the structure of probabilistic graphical models for complex real-valued domains is a formidable computational challenge. This inevitably leads to significant modelling compromises such as discretization or the use of a simplistic Gaussian representation. In this work we address the challenge of efficiently learning truly expressive copula-based networks that facilitate a mix of varied copula families within the same model. Our approach is based on a simple but powerful bivariate building block that is used to highly efficiently perform local model selection, thus bypassing much of computational burden involved in structure learning. We show how this building block can be used to learn general networks and demonstrate its effectiveness on varied and sizeable real-life domains. Importantly, favorable identification and generalization performance come with dramatic runtime improvements. Indeed, the benefits are such that they allow us to tackle domains that are prohibitive when using a standard learning approaches.

Original languageAmerican English
Title of host publicationUncertainty in Artificial Intelligence - Proceedings of the 30th Conference, UAI 2014
EditorsNevin L. Zhang, Jin Tian
Pages790-799
Number of pages10
ISBN (Electronic)9780974903910
StatePublished - 2014
Event30th Conference on Uncertainty in Artificial Intelligence, UAI 2014 - Quebec City, Canada
Duration: 23 Jul 201427 Jul 2014

Publication series

NameUncertainty in Artificial Intelligence - Proceedings of the 30th Conference, UAI 2014

Conference

Conference30th Conference on Uncertainty in Artificial Intelligence, UAI 2014
Country/TerritoryCanada
CityQuebec City
Period23/07/1427/07/14

All Science Journal Classification (ASJC) codes

  • Artificial Intelligence

Cite this