Data-Dependent Bounds for Bayesian Mixture Methods

Ron Meir, Tong Zhang

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

We consider Bayesian mixture approaches, where a predictor is constructed by forming a weighted average of hypotheses from some space of functions. While such procedures are known to lead to optimal predictors in several cases, where sufficiently accurate prior information is available, it has not been clear how they perform when some of the prior assumptions are violated. In this paper we establish data-dependent bounds for such procedures, extending previous randomized approaches such as the Gibbs algorithm to a fully Bayesian setting. The finite-sample guarantees established in this work enable the utilization of Bayesian mixture approaches in agnostic settings, where the usual assumptions of the Bayesian paradigm fail to hold. Moreover, the bounds derived can be directly applied to non-Bayesian mixture approaches such as Bagging and Boosting.

Original languageEnglish (US)
Title of host publicationNIPS 2002
Subtitle of host publicationProceedings of the 15th International Conference on Neural Information Processing Systems
EditorsSuzanna Becker, Sebastian Thrun, Klaus Obermayer
PublisherMIT Press Journals
Pages319-326
Number of pages8
ISBN (Electronic)0262025507, 9780262025508
StatePublished - 2002
Externally publishedYes
Event15th International Conference on Neural Information Processing Systems, NIPS 2002 - Vancouver, Canada
Duration: Dec 9 2002Dec 14 2002

Publication series

NameNIPS 2002: Proceedings of the 15th International Conference on Neural Information Processing Systems

Conference

Conference15th International Conference on Neural Information Processing Systems, NIPS 2002
Country/TerritoryCanada
CityVancouver
Period12/9/0212/14/02

ASJC Scopus subject areas

  • Signal Processing
  • Computer Networks and Communications
  • Information Systems

Fingerprint

Dive into the research topics of 'Data-Dependent Bounds for Bayesian Mixture Methods'. Together they form a unique fingerprint.

Cite this