Proceedings of the Genetic and Evolutionary Computation Conference · 2017 · 86 citations · 20 references
ComputingComputer ScienceAlgorithmsMachine LearningOptimizationContinuous OptimizationMetaheuristic OptimizationMulti-objective OptimizationOptimization For Machine LearningPerformance OptimizationPerformance TuningEmpirical Performance ModelingOptimization Algorithms
Per Instance Algorithm Configuration (PIAC) relies on features that describe problem instances. It builds an Empirical Performance Model (EPM) from a training set made of (instance, parameter configuration) pairs together with the corresponding performance of the algorithm at hand. This paper presents a case study in the continuous black-box optimization domain, using features proposed in the literature. The target algorithm is CMA-ES, and three of its hyper-parameters. Special care is taken to the computational cost of the features. The EPM is learned on the BBOB benchmark, but tested on independent test functions gathered from the optimization literature. The results demonstrate that the proposed approach can outperform the default setting of CMA-ES with as few as 30 or 50 time the problem dimension additional function evaluations for feature computation.
20
ParamILS: An Automatic Algorithm Configuration Framework
Frank Hutter, Holger H. Hoos, Kevin Leyton‐Brown et al. · Journal of Artificial Intelligence Research · 2009 · 868 citations · Full text
SATzilla: Portfolio-based Algorithm Selection for SAT
Lizhong Xu, Frank Hutter, Holger H. Hoos et al. · Journal of Artificial Intelligence Research · 2008 · 835 citations · Full text
A Racing Algorithm for Configuring Metaheuristics
Mauro Birattari, Thomas Stützle, Luís Paquete et al. · 2002 · 488 citations