Poster

Bias-Robust Bayesian Optimization via Dueling Bandits

Johannes Kirschner · Andreas Krause

Keywords: [ Bandits ] [ Reinforcement Learning and Planning ]

[ Abstract ]
[ Paper ]
[ Visit Poster at Spot A6 in Virtual World ]
Tue 20 Jul 9 a.m. PDT — 11 a.m. PDT
 
Spotlight presentation: Auto-ML and Optimization
Tue 20 Jul 5 a.m. PDT — 6 a.m. PDT

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.

Chat is not available.