An Approximate Analytical Approach to Resampling Averages
Malzahn, Doerthe and Opper, Manfred (2003) An Approximate Analytical Approach to Resampling Averages. Journal of Machine Learning Research, 4, 1151-1173.
Download
Full text not available from this repository.
Description/Abstract
Using a novel reformulation, we develop a framework to compute approximate resampling data averages analytically. The method avoids multiple retraining of statistical models on the samples. Our approach uses a combination of the replica ``trick'' of Statistical Physics and the TAP approach for approximate Bayesian inference. We demonstrate our approach on regression with Gaussian processes. A comparison with averages obtained by Monte-Carlo sampling shows that our method achieves good accuracy.
| Item Type: | Article |
|---|---|
| Keywords: | bootstrap, kernel machines, Gaussian processes, approximate inference, statistical physics |
| Divisions: | Faculty of Physical and Applied Science > Electronics and Computer Science |
| Item ID: | 259165 |
| Date Deposited: | 14 Mar 2004 |
| Last Modified: | 01 Mar 2012 10:59 |
| Contributors: | Malzahn, Doerthe (Author) Opper, Manfred (Author) |
| Date: | December 2003 |
| Status: | Published |
| Further Information: | Google Scholar |
| URI: | http://eprints.soton.ac.uk/id/eprint/259165 |
Actions (login required)
 |
View Item |
