Gaussian processes and SVM: Mean field results and leave-one-out

Manfred Opper, Ole Winther

Research output: Chapter in Book/Published conference outputChapter

Abstract

In this chapter, we elaborate on the well-known relationship between Gaussian processes (GP) and Support Vector Machines (SVM). Secondly, we present approximate solutions for two computational problems arising in GP and SVM. The first one is the calculation of the posterior mean for GP classifiers using a `naive' mean field approach. The second one is a leave-one-out estimator for the generalization error of SVM based on a linear response method. Simulation results on a benchmark dataset show similar performances for the GP mean field algorithm and the SVM algorithm. The approximate leave-one-out estimator is found to be in very good agreement with the exact leave-one-out error.
Original languageEnglish
Title of host publicationAdvances in large margin classifiers
EditorsAlex J. Smola, Peter Bartlett, Bernhard Schölkopf, Dale Schuurmans
Place of PublicationCambridge, US
PublisherMIT
Pages43-65
Number of pages23
ISBN (Print)0262194481
Publication statusPublished - Oct 2000

Bibliographical note

Massachusetts Institute of Technology Press (MIT Press) Available on Google Books

Keywords

  • Gaussian processes
  • support vector machines

Fingerprint

Dive into the research topics of 'Gaussian processes and SVM: Mean field results and leave-one-out'. Together they form a unique fingerprint.

Cite this