PASCAL - Pattern Analysis, Statistical Modelling and Computational Learning

Worst-Case Bounds for Gaussian Process Models
Kakade Sham, matthias seeger and Dean Foster
In: Neural Information Processing Systems 2005, Vancouver, Canada(2005).


We present a competitive analysis of some non-parametric Baysian algorithms in a worst-case online learning setting.

EPrint Type:Conference or Workshop Item (Paper)
Project Keyword:Project Keyword UNSPECIFIED
Subjects:Computational, Information-Theoretic Learning with Statistics
Learning/Statistics & Optimisation
Theory & Algorithms
ID Code:1157
Deposited By:matthias seeger
Deposited On:28 November 2005