General Bounds on Bayes Errors for Regression with Gaussian Processes

Opper, Manfred, Vivarelli, Francesco

Neural Information Processing Systems 

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.

Similar Docs  Excel Report  more

TitleSimilaritySource
None found