Timezone: »

 
Poster
Batch Bayesian optimisation via density-ratio estimation with guarantees
Rafael Oliveira · Louis Tiao · Fabio Ramos

Wed Nov 30 09:00 AM -- 11:00 AM (PST) @ Hall J #433
in Poster Session 3 »

Bayesian optimisation (BO) algorithms have shown remarkable success in applications involving expensive black-box functions. Traditionally BO has been set as a sequential decision-making process which estimates the utility of query points via an acquisition function and a prior over functions, such as a Gaussian process. Recently, however, a reformulation of BO via density-ratio estimation (BORE) allowed reinterpreting the acquisition function as a probabilistic binary classifier, removing the need for an explicit prior over functions and increasing scalability. In this paper, we present a theoretical analysis of BORE's regret and an extension of the algorithm with improved uncertainty estimates. We also show that BORE can be naturally extended to a batch optimisation setting by recasting the problem as approximate Bayesian inference. The resulting algorithms come equipped with theoretical performance guarantees and are assessed against other batch and sequential BO baselines in a series of experiments.

Keywords: Gaussian Processes · Bayesian optimization · regret bounds · approximate Bayesian inference · density-ratio estimation
[ Paper]  [ Slides]  [ OpenReview] 

Author Information

Rafael Oliveira (The University of Sydney)
Louis Tiao (University of Sydney)
Fabio Ramos (University of Sydney, NVIDIA)

More from the Same Authors