Randomised Gaussian Process Upper Confidence Bound for Bayesian Optimisation
Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence
Main track. Pages 2284-2290. https://doi.org/10.24963/ijcai.2020/316
In order to improve the performance of Bayesian optimisation, we develop a modified Gaussian process upper confidence bound (GP-UCB) acquisition function. This is done by sampling the exploration-exploitation trade-off parameter from a distribution. We prove that this allows the expected trade-off parameter to be altered to better suit the problem without compromising a bound on the function's Bayesian regret. We also provide results showing that our method achieves better performance than GP-UCB in a range of real-world and synthetic problems.
Machine Learning: Bayesian Optimization
Machine Learning: Cost-Sensitive Learning