A Variational Approach to Learning Curves

Part of Advances in Neural Information Processing Systems 14 (NIPS 2001)

Bibtex Metadata Paper


Dörthe Malzahn, Manfred Opper


We combine the replica approach from statistical physics with a varia- tional approach to analyze learning curves analytically. We apply the method to Gaussian process regression. As a main result we derive ap- proximative relations between empirical error measures, the generaliza- tion error and the posterior variance.