Stochastic performance tuning of complex simulation applications using unsupervised machine learning

Abstract

Machine learning for complex multi-objective problems (MOP) can substantially speedup the discovery of solutions belonging to Pareto landscapes and improve Pareto front accuracy. Studying convergence speedup of multi-objective search on well-known benchmarks is an important step in the development of algorithms to optimize complex problems such as High Energy Physics particle transport simulations. In this paper we will describe how we perform this optimization via a tuning based on genetic algorithms and machine learning for MOP. One of the approaches described is based on the introduction of a specific multivariate analysis operator that can be used in case of expensive fitness function evaluations, in order to speed-up the convergence of the “black-box” optimization problem.