English

Bias-Robust Bayesian Optimization via Dueling Bandits

Machine Learning 2021-06-10 v2 Machine Learning

Abstract

We consider Bayesian optimization in settings where observations can be adversarially biased, for example by an uncontrolled hidden confounder. Our first contribution is a reduction of the confounded setting to the dueling bandit model. Then we propose a novel approach for dueling bandits based on information-directed sampling (IDS). Thereby, we obtain the first efficient kernelized algorithm for dueling bandits that comes with cumulative regret guarantees. Our analysis further generalizes a previously proposed semi-parametric linear bandit model to non-linear reward functions, and uncovers interesting links to doubly-robust estimation.

Keywords

Cite

@article{arxiv.2105.11802,
  title  = {Bias-Robust Bayesian Optimization via Dueling Bandits},
  author = {Johannes Kirschner and Andreas Krause},
  journal= {arXiv preprint arXiv:2105.11802},
  year   = {2021}
}
R2 v1 2026-06-24T02:26:25.677Z