Extracting certainty from uncertainty: regret bounded by variation in costs
- 29 April 2010
- journal article
- Published by Springer Nature in Machine Learning
- Vol. 80 (2-3) , 165-188
Abstract
No abstract availableKeywords
This publication has 11 references indexed in Scilit:
- Better Algorithms for Benign Bandits2009
- Prediction, Learning, and Games2006
- Efficient algorithms for online decision problemsJournal of Computer and System Sciences, 2005
- Full Information Game with Gains and Losses2004
- The Nonstochastic Multiarmed Bandit ProblemSIAM Journal on Computing, 2002
- Relative loss bounds for single neuronsIEEE Transactions on Neural Networks, 1999
- A Decision-Theoretic Generalization of On-Line Learning and an Application to BoostingJournal of Computer and System Sciences, 1997
- Exponentiated Gradient versus Gradient Descent for Linear PredictorsInformation and Computation, 1997
- The Weighted Majority AlgorithmInformation and Computation, 1994
- Universal PortfoliosMathematical Finance, 1991