General bounds on Bayes errors for regression with Gaussian processes


Based on a simple convexity lemma, we develop bounds for different types of Bayesian prediction errors for regression with Gaussian processes. The basic bounds are formulated for a fixed training set. Simpler expressions are obtained for sampling from an input distribution which equals the weight function of the covariance kernel, yielding asymptotically tight results. The results are compared with numerical experiments.

Divisions: Aston University (General)
Additional Information: Copyright of the Massachusetts Institute of Technology Press (MIT)
Event Title: 12th Annual Conference on Neural Information Processing Systems, NIPS 1998
Event Type: Other
Event Dates: 1998-11-30 - 1998-12-05
Uncontrolled Keywords: convexity,Bayesian prediction errors,regression,Gaussian processes,covariance kernel,asymptotically,Computer Networks and Communications,Information Systems,Signal Processing
ISBN: 978-026211245-1
Last Modified: 09 May 2024 07:26
Date Deposited: 15 Sep 2009 15:57
Full Text Link:
Related URLs: http://www.scop ... tnerID=8YFLogxK (Scopus URL)
http://mitpress ... type=2&tid=4746 (Publisher URL)
PURE Output Type: Conference contribution
Published Date: 1999
Authors: Opper, Manfred
Vivarelli, Francesco



Version: Published Version

Export / Share Citation


Additional statistics for this record