A new acquisition function for robust Bayesian optimization of unconstrained problems

Genetic and Evolutionary Computation Conference Companion (GECCO Companion), pp. 1344–1345

Abstract

A new acquisition function is proposed for solving robust optimization problems via Bayesian Optimization. The proposed acquisition function reflects the need for the robust instead of the nominal optimum, and is based on the intuition of utilizing the higher moments of the improvement. The efficacy of Bayesian Optimization based on this acquisition function is demonstrated on four test problems, each affected by three different levels of noise. Our findings suggest the promising nature of the proposed acquisition function as it yields a better robust optimal value of the function in 6/12 test scenarios when compared with the baseline.

Authors 5

1. Sibghat Ullah Aachen

   Leiden University

   Affiliation as printed

   Leiden University, Leiden, The Netherlands

2. Hao Wang Aachen

   Leiden University

   Affiliation as printed

   Leiden University, Leiden, The Netherlands

3. Stefan Menzel

   Honda (Germany)

   Affiliation as printed

   Honda Research Institute Europe, Offenbach/Main, Germany

4. Bernhard Sendhoff

   Honda (Germany)

   Affiliation as printed

   Honda Research Institute Europe, Offenbach/Main, Germany

5. Thomas Bäck Aachen

   Leiden University

   Affiliation as printed

   Leiden University, Leiden, The Netherlands