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.
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}
}