Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Bayesian Optimistic Optimisation with Exponentially Decaying Regret

About

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 $\mathcal{O}(\frac{logN}{\sqrt{N}})$ to $\mathcal O(e^{-\sqrt{N}})$, where $N$ 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 $\mathcal O(N^{-\sqrt{N}})$ under the assumption that the objective function is sampled from a Gaussian process with a Mat\'ern kernel with smoothness parameter $\nu > 4 +\frac{D}{2}$, where $D$ 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.

Hung Tran-The, Sunil Gupta, Santu Rana, Svetha Venkatesh• 2021

Related benchmarks

TaskDatasetResultRank
Black-box OptimizationHartmann3
Average CPU Time (s)27.21
13
OptimizationShekel d=4
Average CPU Time (s)91.22
6
OptimizationSchwefel D=3
Average CPU Time (s)41.01
6
Showing 3 of 3 rows

Other info

Follow for update