Tracking the best of many experts

Authors:
András György;Tamás Linder;Gábor Lugosi
Affiliations:
Informatics Laboratory, Computer and Automation Research Institute of the Hungarian Academy of Sciences, Budapest, Hungary;Department of Mathematics and Statistics, Queen's University, Kingston, Ontario, Canada;Department of Economics, Universitat Pompeu Fabra, Barcelona, Spain
Venue:
COLT'05 Proceedings of the 18th annual conference on Learning Theory
Year:
2005

Citing 14
Cited 4

Aggregating strategies

COLT '90 Proceedings of the third annual workshop on Computational learning theory
The weighted majority algorithm

Information and Computation
Predicting Nearly As Well As the Best Pruning of a Decision Tree

Machine Learning - Special issue on the eighth annual conference on computational learning theory, (COLT '95)
How to use expert advice

Journal of the ACM (JACM)
Tracking the Best Disjunction

Machine Learning - Special issue on context sensitivity and concept drift
Tracking the Best Expert

Machine Learning - Special issue on context sensitivity and concept drift
Derandomizing Stochastic Prediction Strategies

Machine Learning - Special issue: computational learning theory, COLT '97
An Efficient Extension to Mixture Techniques for Prediction and Decision Trees

Machine Learning
Predicting nearly as well as the best pruning of a planar decision graph

Theoretical Computer Science
Path Kernels and Multiplicative Updates

COLT '02 Proceedings of the 15th Annual Conference on Computational Learning Theory
Tracking the best linear predictor

The Journal of Machine Learning Research
Tracking a small set of experts by mixing past posteriors

The Journal of Machine Learning Research
Path kernels and multiplicative updates

The Journal of Machine Learning Research
Efficient adaptive algorithms and minimax bounds for zero-delay lossy source coding

IEEE Transactions on Signal Processing

Following the Perturbed Leader to Gamble at Multi-armed Bandits

ALT '07 Proceedings of the 18th international conference on Algorithmic Learning Theory
Combining initial segments of lists

ALT'11 Proceedings of the 22nd international conference on Algorithmic learning theory
The shortest path problem under partial monitoring

COLT'06 Proceedings of the 19th annual conference on Learning Theory
Combining initial segments of lists

Theoretical Computer Science

Quantified Score

Hi-index	0.00

Visualization

Abstract

An algorithm is presented for online prediction that allows to track the best expert efficiently even if the number of experts is exponentially large, provided that the set of experts has a certain structure allowing efficient implementations of the exponentially weighted average predictor. As an example we work out the case where each expert is represented by a path in a directed graph and the loss of each expert is the sum of the weights over the edges in the path.