PASCAL - Pattern Analysis, Statistical Modelling and Computational Learning

Combining Expert Advice Efficiently
Wouter Koolen and Steven de Rooij
In: COLT 2008, 9-12 July 2008, Helsinki, Finland.

Abstract

We show how models for prediction with expert advice can be defined concisely and clearly using Hidden Markov Models (HMMs); standard HMM algorithms can then be used to efficiently calculate, among other things, how the expert predictions should be weighted according to the model. We review existing models and shed new light on their relationships. We pay special attention to the Switch-Distribution, which was recently developed to improve Bayesian/Minimum Description Length model selection. We explain how the required calculations can be performed efficiently.

EPrint Type:Conference or Workshop Item (Paper)
Project Keyword:Project Keyword UNSPECIFIED
Subjects:Computational, Information-Theoretic Learning with Statistics
Learning/Statistics & Optimisation
ID Code:3472
Deposited By:Wouter Koolen
Deposited On:11 February 2008