Lenient Regret and Good-Action Identification in Gaussian Process Bandits

Abstract

In this paper, we study the problem of Gaussian process (GP) bandits under relaxed optimization criteria stating that any function value above a certain threshold is "good enough". On the theoretical side, we study various {\em lenient regret} notions in which all near-optimal actions incur zero penalty, and provide upper bounds on the lenient regret for GP-UCB and an elimination algorithm, circumventing the usual $O(\sqrt{T})$ term (with time horizon $T$) resulting from zooming extremely close towards the function maximum. In addition, we complement these upper bounds with algorithm-independent lower bounds. On the practical side, we consider the problem of finding a single "good action" according to a known pre-specified threshold, and introduce several good-action identification algorithms that exploit knowledge of the threshold. We experimentally find that such algorithms can often find a good action faster than standard optimization-based approaches.

arXiv commentICML 2021

References in corpus (8)

• Predictive Entropy Search for Efficient Global Optimization of Black-box Functions
• Max-value Entropy Search for Efficient Bayesian Optimization
• Finite-Time Analysis of Kernelised Contextual Bandits
• Truncated Variance Reduction: A Unified Approach to Bayesian Optimization and Level-Set Estimation
• Lower Bounds on Regret for Noisy Gaussian Process Bandit Optimization
• On Kernelized Multi-armed Bandits
• The True Sample Complexity of Identifying Good Arms
• Lenient Regret for Multi-Armed Bandits

Cited by in corpus (2)

• Gaussian Process Bandit Optimization with Few Batches
• Adversarial Attacks on Gaussian Process Bandits