Scalable Bayesian Optimization with Sparse Gaussian Process Models

TL;DR

This paper introduces scalable Bayesian optimization techniques that leverage derivative information and sparse Gaussian process models to improve convergence speed and handle large datasets efficiently.

Contribution

It presents novel methods combining derivative-enhanced Bayesian optimization with scalable GPs for large-scale problems.

Findings

Accelerated convergence using derivative information.

Effective handling of large datasets with sparse GPs.

Improved scalability of Bayesian optimization.

Abstract

This thesis focuses on Bayesian optimization with the improvements coming from two aspects:(i) the use of derivative information to accelerate the optimization convergence; and (ii) the consideration of scalable GPs for handling massive data.