Algorithm Selection as a Bandit Problem with Unbounded Losses
Authors:
- 1 January 2010
- book chapter
- Published by Springer Nature in Lecture Notes in Computer Science
- p. 82-96
Abstract
No abstract availableKeywords
All Related Versions
This publication has 25 references indexed in Scilit:
- Cross-disciplinary perspectives on meta-learning for algorithm selectionACM Computing Surveys, 2009
- Learning dynamic algorithm portfoliosAnnals of Mathematics and Artificial Intelligence, 2007
- Learning parallel portfolios of algorithmsAnnals of Mathematics and Artificial Intelligence, 2006
- APPLYING MACHINE LEARNING TO LOW-KNOWLEDGE CONTROL OF OPTIMIZATION ALGORITHMSComputational Intelligence, 2005
- Introduction to the Special Issue on Meta-LearningMachine Learning, 2004
- The Nonstochastic Multiarmed Bandit ProblemSIAM Journal on Computing, 2002
- Algorithm portfoliosArtificial Intelligence, 2001
- An Economics Approach to Hard Computational ProblemsScience, 1997
- The Weighted Majority AlgorithmInformation and Computation, 1994
- Some aspects of the sequential design of experimentsBulletin of the American Mathematical Society, 1952