Regret Analysis for Randomized Gaussian Process Upper Confidence Bound

TL;DR

This paper introduces IRGP-UCB, a randomized variant of GP-UCB for Bayesian optimization, which achieves sub-linear regret bounds without increasing the confidence parameter, unlike traditional methods.

Contribution

It proposes IRGP-UCB with a novel confidence parameter derived from a shifted exponential distribution, improving regret bounds in finite domains.

Findings

IRGP-UCB achieves sub-linear regret bounds.

Randomization prevents linear regret growth.

Numerical experiments validate theoretical results.

Abstract

Gaussian process upper confidence bound (GP-UCB) is a theoretically established algorithm for Bayesian optimization (BO), where we assume the objective function $f$ follows a GP. One notable drawback of GP-UCB is that the theoretical confidence parameter $\beta$ increases along with the iterations and is too large. To alleviate this drawback, this paper analyzes the randomized variant of GP-UCB called improved randomized GP-UCB (IRGP-UCB), which uses the confidence parameter generated from the shifted exponential distribution. We analyze the expected regret and conditional expected regret, where the expectation and the probability are taken respectively with $f$ and noise and with the randomness of the BO algorithm. In both regret analyses, IRGP-UCB achieves a sub-linear regret upper bound without increasing the confidence parameter if the input domain is finite. Furthermore, we show that randomization plays a key role in avoiding an increase in confidence parameter by showing that GP-UCB using a constant confidence parameter can incur linearly growing expected cumulative regret. Finally, we show numerical experiments using synthetic and benchmark functions and real-world emulators.