Bias-Robust Bayesian Optimization via Dueling Bandits

Johannes Kirschner · Andreas Krause

[ Abstract ] [ Livestream: Visit Auto-ML and Optimization ] [ Paper ]
Tue 20 Jul 5:30 a.m. — 5:35 a.m. PDT

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.

Chat is not available.