Lower Bounds on Regret for Noisy Gaussian Process Bandit Optimization

TL;DR

This paper establishes fundamental lower bounds on the regret in noisy Gaussian process bandit optimization, revealing the minimal achievable performance and highlighting gaps with existing algorithms.

Contribution

It provides the first algorithm-independent lower bounds on simple and cumulative regret for Gaussian process bandit optimization with smooth kernels.

Findings

Lower bounds match existing upper bounds up to logarithmic factors.

Bounds are derived for squared-exponential and Matérn kernels.

Results highlight fundamental limits of optimization performance in noisy settings.

Abstract

In this paper, we consider the problem of sequentially optimizing a black-box function $f$ based on noisy samples and bandit feedback. We assume that $f$ is smooth in the sense of having a bounded norm in some reproducing kernel Hilbert space (RKHS), yielding a commonly-considered non-Bayesian form of Gaussian process bandit optimization. We provide algorithm-independent lower bounds on the simple regret, measuring the suboptimality of a single point reported after $T$ rounds, and on the cumulative regret, measuring the sum of regrets over the $T$ chosen points. For the isotropic squared-exponential kernel in $d$ dimensions, we find that an average simple regret of $\epsilon$ requires $T = \Omega\big(\frac{1}{\epsilon^2} (\log\frac{1}{\epsilon})^{d/2}\big)$, and the average cumulative regret is at least $\Omega\big( \sqrt{T(\log T)^{d/2}} \big)$, thus matching existing upper bounds up to the replacement of $d/2$ by $2d+O(1)$ in both cases. For the Mat\'ern-$\nu$ kernel, we give analogous bounds of the form $\Omega\big( (\frac{1}{\epsilon})^{2+d/\nu}\big)$ and $\Omega\big( T^{\frac{\nu + d}{2\nu + d}} \big)$, and discuss the resulting gaps to the existing upper bounds.