Mixture of vector experts

Authors:
Matthew Henderson;John Shawe-Taylor;Janez Žerovnik
Affiliations:
School of Electronics and Computer Science, University of Southampton, Southampton, England;School of Electronics and Computer Science, University of Southampton, Southampton, England;Institute of Mathematics, Physics and Mechanics, Ljubljana, Slovenia
Venue:
ALT'05 Proceedings of the 16th international conference on Algorithmic Learning Theory
Year:
2005

Citing 3
Cited 0

Aggregating strategies

COLT '90 Proceedings of the third annual workshop on Computational learning theory
How to use expert advice

Journal of the ACM (JACM)
Sequential prediction of individual sequences under general loss functions

IEEE Transactions on Information Theory

Quantified Score

Hi-index	0.00

Visualization

Abstract

We describe and analyze an algorithm for predicting a sequence of n-dimensional binary vectors based on a set of experts making vector predictions in [0,1]n. We measure the loss of individual predictions by the 2-norm between the actual outcome vector and the prediction. The loss of an expert is then the sum of the losses experienced on individual trials. We obtain bounds for the loss of our expert algorithm in terms of the loss of the best expert analogous to the well-known results for scalar experts making real-valued predictions of a binary outcome.