Particle learning of Gaussian process models for sequential design and optimization

TL;DR

This paper introduces a particle learning method using sequential Monte Carlo for online updating of Gaussian process models, enabling efficient sequential design and active learning in optimization and classification tasks.

Contribution

The paper presents a simulation-based SMC approach for real-time Gaussian process model updating, offering a faster alternative to traditional MCMC methods for sequential design and active learning.

Findings

SMC-based method outperforms MCMC in speed for sequential updates

Enables online active learning for noisy function optimization

Facilitates exploration of classification boundaries in real-time

Abstract

We develop a simulation-based method for the online updating of Gaussian process regression and classification models. Our method exploits sequential Monte Carlo to produce a fast sequential design algorithm for these models relative to the established MCMC alternative. The latter is less ideal for sequential design since it must be restarted and iterated to convergence with the inclusion of each new design point. We illustrate some attractive ensemble aspects of our SMC approach, and show how active learning heuristics may be implemented via particles to optimize a noisy function or to explore classification boundaries online.