Bayesian Optimistic Optimisation with Exponentially Decaying Regret
Abstract
Bayesian optimisation (BO) is a well-known efficient algorithm for finding the global optimum of expensive, black-box functions. The current practical BO algorithms have regret bounds ranging from to , where is the number of evaluations. This paper explores the possibility of improving the regret bound in the noiseless setting by intertwining concepts from BO and tree-based optimistic optimisation which are based on partitioning the search space. We propose the BOO algorithm, a first practical approach which can achieve an exponential regret bound with order under the assumption that the objective function is sampled from a Gaussian process with a Mat\'ern kernel with smoothness parameter , where is the number of dimensions. We perform experiments on optimisation of various synthetic functions and machine learning hyperparameter tuning tasks and show that our algorithm outperforms baselines.
Cite
@article{arxiv.2105.04332,
title = {Bayesian Optimistic Optimisation with Exponentially Decaying Regret},
author = {Hung Tran-The and Sunil Gupta and Santu Rana and Svetha Venkatesh},
journal= {arXiv preprint arXiv:2105.04332},
year = {2026}
}
Comments
To appear at ICML 2021 (21 pages)