Algorithm portfolio selection as a bandit problem with unbounded losses

DOI10.1007/S10472-011-9228-ZzbMath1234.68339OpenAlexW1983691438MaRDI QIDQ408989

Matteo Gagliolo, Jürgen Schmidhuber

Publication date: 12 April 2012

Published in: Annals of Mathematics and Artificial Intelligence (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1007/s10472-011-9228-z

zbMATH Keywords

computational complexitycombinatorial optimizationsurvival analysisonline learningsatisfiabilityalgorithm portfoliosconstraint programmingalgorithm selectionmulti-armed bandit problemLas Vegas algorithmsmeta learning

Mathematics Subject Classification ID

Analysis of algorithms and problem complexity (68Q25) Learning and adaptive systems in artificial intelligence (68T05) Survival analysis and censored data (62N99) Problem solving in the context of artificial intelligence (heuristics, search strategies, etc.) (68T20) Nonparametric inference (62G99) Online algorithms; streaming algorithms (68W27)

Related Items (4)

Variable ordering for decision diagrams: a portfolio approach ⋮ Multi-armed bandits with censored consumption of resources ⋮ Analyzing bandit-based adaptive operator selection mechanisms ⋮ \textsc{Alors}: an algorithm recommender system

Uses Software

• SATzilla
• SPOT

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Optimal speedup of Las Vegas algorithms
• Learning dynamic algorithm portfolios
• Reactive search and intelligent optimization
• The weighted majority algorithm
• Survival analysis. Techniques for censored and truncated data.
• Heavy-tailed phenomena in satisfiability and constraint satisfaction problems
• Learning parallel portfolios of algorithms
• Algorithm Survival Analysis
• Nonparametric Estimation from Incomplete Observations
• Hannan Consistency in On-Line Learning in Case of Unbounded Losses Under Partial Monitoring
• Minimizing Regret With Label Efficient Prediction
• The Nonstochastic Multiarmed Bandit Problem
• Combining Multiple Heuristics
• Machine Learning: ECML 2004
• Learning Theory
• Some aspects of the sequential design of experiments
• Principles and Practice of Constraint Programming – CP 2004
• Algorithm portfolios

This page was built for publication: Algorithm portfolio selection as a bandit problem with unbounded losses