Bayesian Optimization in Theory and Practice

Abstract

Bayesian optimization is a useful tool for sample-efficient optimization of expensive-to-evaluate black-box functions. In the first part of the talk, we will have a look at a motivating robotics example, where Bayesian optimization can be used for learning gaits of a walking robot. In the second part, we will investigate some intricate details of the inner workings of Bayesian optimization, i.e., the acquisition function (which tells us which experiment to conduct next) and how to optimize it efficiently.

Date
Event
Huawei Science and Technology Workshop
Location
virtual
Avatar
Marc Deisenroth
DeepMind Chair of Machine Learning and Artificial Intelligence