A Statistical Mechanics Approach to Approximate Analytical Bootstrap Averages

Dorthe Malzahn; Manfred Opper; Becker, Becker S. et al.

A Statistical Mechanics Approach to Approximate Analytical Bootstrap Averages

Dorthe Malzahn, Manfred Opper, Becker, Becker S. et al. (Editor)

Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review

38 Downloads (Pure)

Abstract

We 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.

Original language	English
Title of host publication	Advances in Neural Information Processing Systems 15
Publisher	MIT Press
Publication date	2003
Publication status	Published - 2003

Access to Document

Imm1512

http://www.imm.dtu.dk/pubdb/p.php?1512

SFX availability

Full text

Cite this

@inproceedings{2cd950858e6f463f8e69ac7f0277b233,

title = "A Statistical Mechanics Approach to Approximate Analytical Bootstrap Averages",

abstract = "We 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.",

keywords = "variational methods, Bootstrap, learning curves, statistical physics, Gaussian processes",

author = "Dorthe Malzahn and Manfred Opper and {Becker S. et al.}, Becker,",

year = "2003",

language = "English",

booktitle = "Advances in Neural Information Processing Systems 15",

publisher = "MIT Press",

}

TY - GEN

T1 - A Statistical Mechanics Approach to Approximate Analytical Bootstrap Averages

AU - Malzahn, Dorthe

AU - Opper, Manfred

A2 - Becker S. et al., Becker,

PY - 2003

Y1 - 2003

N2 - We 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.

AB - We 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.

KW - variational methods

KW - Bootstrap

KW - learning curves

KW - statistical physics

KW - Gaussian processes

M3 - Article in proceedings

BT - Advances in Neural Information Processing Systems 15

PB - MIT Press

ER -

A Statistical Mechanics Approach to Approximate Analytical Bootstrap Averages

Abstract

Access to Document

SFX availability

Fingerprint

Cite this