cs.LGOct 30, 2026

RaMMOBO: Random Max-Margin Multi-Objective Bayesian Optimization

Authors: Thomas Wedenig, Paul Plantosar, Robert Peharz

Organizations: Institute of Machine Learning and Neural Computation, TU Graz, Austria · Graz Center for Machine Learning (GraML), Austria

Abstract

Multi-objective Bayesian optimization (MOBO) maximizes MM expensive black-box objectives with the goal of approximating the Pareto set, whose objective vectors cannot be improved in one component without sacrificing another. A common quality measure is hypervolume, the volume in objective space dominated by these vectors relative to a reference point. Expected hypervolume improvement (EHVI) directly targets this metric and is one-step Bayes-optimal, but its standard computation scales exponentially with MM, making it prohibitively expensive for many-objective problems. We introduce random max-margin multi-objective Bayesian optimization (RaMMOBO), whose acquisition function lower-bounds EHVI while requiring only linear cost in MM to evaluate. RaMMOBO measures the volume of a max-margin box contained in a candidate's hypervolume-improvement region and averages over random reweightings of the objective space, yielding a utility that is strictly Pareto-monotone on hypervolume-improving outcomes. It naturally handles noisy observations and different probabilistic surrogates and supports efficient gradient-based optimization. Across synthetic and real-world benchmarks, RaMMOBO matches or outperforms state-of-the-art methods, with largest gains at higher MM, with acquisition optimization up to two orders of magnitude faster than qLogNEHVI. Our implementation is available at https://anonymous.4open.science/r/rammobo.

Figures & tables

Appendix figures & tables8 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. Multi-Objective Bayesian Optimization via Adaptive \varepsilon-Constraints Decomposition

    Apr 17, 2026Yaohong Yang, Sammie Katt, Samuel KaskiBayesian OptimizationMulti-Objective Optimization

  2. High-dimensional Multi-objective Bayesian Optimization with Learned Variable Interactions

    Aug 12, 2026Hongyan Wang, Jiayu Huang, Haotian Zheng +6Bayesian OptimizationBlack-Box Optimization

  3. mlr3mbo: Bayesian Optimization in R

    Mar 31, 2026Marc Becker, Lennart Schneider, Martin Binder +2Bayesian OptimizationHyperparameter Optimization