Bayesian optimization using sequential Monte Carlo

Romain Benassi (1, 2) , Julien Bect (2) , Emmanuel Vazquez (2)

1 GdR MASCOT-NUM - Méthodes d'Analyse Stochastique des Codes et Traitements Numériques
2 E3S - Supélec Sciences des Systèmes

We consider the problem of optimizing a real-valued continuous function $f$ using a Bayesian approach, where the evaluations of $f$ are chosen sequentially by combining prior information about $f$, which is described by a random process model, and past evaluation results. The main difficulty with this approach is to be able to compute the posterior distributions of quantities of interest which are used to choose evaluation points. In this article, we decide to use a Sequential Monte Carlo (SMC) approach.

Domains: Statistics [stat]; Machine Learning [stat.ML]; Mathematics [math]; Optimization and Control [math.OC]

Romain Benassi, Julien Bect, Emmanuel Vazquez. Bayesian optimization using sequential Monte Carlo. 6th International Conference on Learning and Intelligent Optimization (LION6), Jan 2012, Paris, France. pp.339-342, ⟨10.1007/978-3-642-34413-8_24⟩. ⟨hal-00717195⟩