Multitask learning with expert advice
Data(s) |
28/01/2007
|
---|---|
Resumo |
We consider the problem of prediction with expert advice in the setting where a forecaster is presented with several online prediction tasks. Instead of competing against the best expert separately on each task, we assume the tasks are related, and thus we expect that a few experts will perform well on the entire set of tasks. That is, our forecaster would like, on each task, to compete against the best expert chosen from a small set of experts. While we describe the "ideal" algorithm and its performance bound, we show that the computation required for this algorithm is as hard as computation of a matrix permanent. We present an efficient algorithm based on mixing priors, and prove a bound that is nearly as good for the sequential task presentation case. We also consider a harder case where the task may change arbitrarily from round to round, and we develop an efficient approximate randomized algorithm based on Markov chain Monte Carlo techniques. |
Identificador | |
Publicador |
University of California |
Relação |
http://www.eecs.berkeley.edu/Pubs/TechRpts/2007/EECS-2007-20.pdf Abernethy, Jacob D., Bartlett, Peter L., & Rakhlin, Alexander (2007) Multitask learning with expert advice. Technical Report, UCB/EECS-2007-20. University of California, Berkeley, California. |
Direitos |
Copyright © 2007, by the author(s). All rights reserved. Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. To copy otherwise, to republish, to post on servers or to redistribute to lists, requires prior specific permission. |
Fonte |
Faculty of Science and Technology; Mathematical Sciences |
Palavras-Chave | #080100 ARTIFICIAL INTELLIGENCE AND IMAGE PROCESSING #OAVJ |
Tipo |
Report |