Bias-Robust Bayesian Optimization via Dueling Bandits

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.

References in corpus (2)

• Correlational Dueling Bandits with Application to Clinical Treatment in Large Decision Spaces
• Contextual Multi-armed Bandit Algorithm for Semiparametric Reward Model