Cross-disciplinary perspectives on meta-learning for algorithm selection
ACM Computing Surveys (CSUR)
Data mining for simulation algorithm selection
Proceedings of the 2nd International Conference on Simulation Tools and Techniques
Empirical hardness models: Methodology and a case study on combinatorial auctions
Journal of the ACM (JACM)
An Efficient and Adaptive Mechanism for Parallel Simulation Replication
PADS '09 Proceedings of the 2009 ACM/IEEE/SCS 23rd Workshop on Principles of Advanced and Distributed Simulation
Efficient Multi-start Strategies for Local Search Algorithms
ECML PKDD '09 Proceedings of the European Conference on Machine Learning and Knowledge Discovery in Databases: Part I
SATzilla: portfolio-based algorithm selection for SAT
Journal of Artificial Intelligence Research
IJCAI'07 Proceedings of the 20th international joint conference on Artifical intelligence
SATenstein: automatically building local search SAT solvers from components
IJCAI'09 Proceedings of the 21st international jont conference on Artifical intelligence
SATzilla-07: the design and analysis of an algorithm portfolio for SAT
CP'07 Proceedings of the 13th international conference on Principles and practice of constraint programming
Algorithm selection as a bandit problem with unbounded losses
LION'10 Proceedings of the 4th international conference on Learning and intelligent optimization
Automating the runtime performance evaluation of simulation algorithms
Winter Simulation Conference
Optimization of heuristic search using recursive algorithm selection and reinforcement learning
Annals of Mathematics and Artificial Intelligence
A portfolio solver for answer set programming: preliminary report
LPNMR'11 Proceedings of the 11th international conference on Logic programming and nonmonotonic reasoning
Selecting Simulation Algorithm Portfolios by Genetic Algorithms
PADS '10 Proceedings of the 2010 IEEE Workshop on Principles of Advanced and Distributed Simulation
Enhancing accuracy of hybrid packing systems through general-purpose characterization
HAIS'11 Proceedings of the 6th international conference on Hybrid artificial intelligent systems - Volume Part II
Review: Measuring instance difficulty for combinatorial optimization problems
Computers and Operations Research
Bayesian networks to predict data mining algorithm behavior in ubiquitous computing environments
MSM'10/MUSE'10 Proceedings of the 2010 international conference on Analysis of social media and ubiquitous data
Efficient multi-start strategies for local search algorithms
Journal of Artificial Intelligence Research
Algorithm portfolio selection as a bandit problem with unbounded losses
Annals of Mathematics and Artificial Intelligence
Evaluating component solver contributions to portfolio-based algorithm selectors
SAT'12 Proceedings of the 15th international conference on Theory and Applications of Satisfiability Testing
Learning algorithm portfolios for parallel execution
LION'12 Proceedings of the 6th international conference on Learning and Intelligent Optimization
Evaluating simulation software components with player rating systems
Proceedings of the 6th International ICST Conference on Simulation Tools and Techniques
Towards objective measures of algorithm performance across instance space
Computers and Operations Research
| Hi-index | 0.00 |
Algorithm selection can be performed using a model of runtime distribution, learned during a preliminary training phase. There is a trade-off between the performance of model-based algorithm selection, and the cost of learning the model. In this paper, we treat this trade-off in the context of bandit problems. We propose a fully dynamic and online algorithm selection technique, with no separate training phase: all candidate algorithms are run in parallel, while a model incrementally learns their runtime distributions. A redundant set of time allocators uses the partially trained model to propose machine time shares for the algorithms. A bandit problem solver mixes the model-based shares with a uniform share, gradually increasing the impact of the best time allocators as the model improves. We present experiments with a set of SAT solvers on a mixed SAT-UNSAT benchmark; and with a set of solvers for the Auction Winner Determination problem.