A Statistical Mechanics Approach to Approximate Analytical Bootstrap Averages

Dörthe Malzahn, Manfred Opper

AbstractWe apply the replica method of Statistical Physics combined with a
variational method to the approximate analytical computation of bootstrap
averages for estimating the generalization error. We demonstrate our
approach on regression with Gaussian processes and compare our
results with averages obtained by Monte-Carlo sampling.
KeywordsBootstrap, learning curves, Gaussian processes, statistical physics, variational methods
TypeConference paper [With referee]
ConferenceAdvances in Neural Information Processing Systems 15
EditorsS. Becker, S. Thrun, K. Obermayer
PublisherMIT Press
Electronic version(s)[ps]
BibTeX data [bibtex]
IMM Group(s)Intelligent Signal Processing

Back  ::  IMM Publications