Skip to yearly menu bar Skip to main content


Poster

Regret bounds for meta Bayesian optimization with an unknown Gaussian process prior

Zi Wang · Beomjoon Kim · Leslie Kaelbling

Room 210 #22

Keywords: [ Bandit Algorithms ] [ Gaussian Processes ]


Abstract:

Bayesian optimization usually assumes that a Bayesian prior is given. However, the strong theoretical guarantees in Bayesian optimization are often regrettably compromised in practice because of unknown parameters in the prior. In this paper, we adopt a variant of empirical Bayes and show that, by estimating the Gaussian process prior from offline data sampled from the same prior and constructing unbiased estimators of the posterior, variants of both GP-UCB and \emph{probability of improvement} achieve a near-zero regret bound, which decreases to a constant proportional to the observational noise as the number of offline data and the number of online evaluations increase. Empirically, we have verified our approach on challenging simulated robotic problems featuring task and motion planning.

Live content is unavailable. Log in and register to view live content