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.
Related benchmarks
| Task | Dataset | Result | Rank | |
|---|---|---|---|---|
| Black-box Optimization | Hartmann3 | Average CPU Time (s)27.21 | 13 | |
| Optimization | Shekel d=4 | Average CPU Time (s)91.22 | 6 | |
| Optimization | Schwefel D=3 | Average CPU Time (s)41.01 | 6 |