Randomized Gaussian Process Upper Confidence Bound with Tight Bayesian Regret Bounds

by   Shion Takeno, et al.

Gaussian process upper confidence bound (GP-UCB) is a theoretically promising approach for black-box optimization; however, the confidence parameter β is considerably large in the theorem and chosen heuristically in practice. Then, randomized GP-UCB (RGP-UCB) uses a randomized confidence parameter, which follows the Gamma distribution, to mitigate the impact of manually specifying β. This study first generalizes the regret analysis of RGP-UCB to a wider class of distributions, including the Gamma distribution. Furthermore, we propose improved RGP-UCB (IRGP-UCB) based on a two-parameter exponential distribution, which achieves tight Bayesian regret bounds. IRGP-UCB does not require an increase in the confidence parameter in terms of the number of iterations, which avoids over-exploration in the later iterations. Finally, we demonstrate the effectiveness of IRGP-UCB through extensive experiments.


page 1

page 2

page 3

page 4


Randomised Gaussian Process Upper Confidence Bound for Bayesian Optimisation

In order to improve the performance of Bayesian optimisation, we develop...

Parallel Gaussian Process Optimization with Upper Confidence Bound and Pure Exploration

In this paper, we consider the challenge of maximizing an unknown functi...

Scalable Thompson Sampling using Sparse Gaussian Process Models

Thompson Sampling (TS) with Gaussian Process (GP) models is a powerful t...

Multi-Scale Zero-Order Optimization of Smooth Functions in an RKHS

We aim to optimize a black-box function f:XR under the assumption that f...

Regret Bounds for Gaussian-Process Optimization in Large Domains

The goal of this paper is to characterize Gaussian-Process optimization ...

Gaussian Process Optimization with Adaptive Sketching: Scalable and No Regret

Gaussian processes (GP) are a popular Bayesian approach for the optimiza...

Active Assessment of Prediction Services as Accuracy Surface Over Attribute Combinations

Our goal is to evaluate the accuracy of a black-box classification model...

Please sign up or login with your details

Forgot password? Click here to reset