Multi-Objective Bayesian Optimization for Accelerator Tuning

TL;DR

This paper presents a multi-objective Bayesian optimization method tailored for online accelerator tuning, significantly reducing the number of beam measurements needed to find optimal trade-offs between multiple objectives.

Contribution

It introduces a Gaussian process-based multi-objective Bayesian optimization framework specifically designed for real-time accelerator tuning, overcoming limitations of traditional offline methods.

Findings

Reduces measurement requirements by at least an order of magnitude.

Efficiently finds the full Pareto front in a serialized manner.

Incorporates constraints, preferences, and costs into the optimization process.

Abstract

Particle accelerators require constant tuning during operation to meet beam quality, total charge and particle energy requirements for use in a wide variety of physics, chemistry and biology experiments. Maximizing the performance of an accelerator facility often necessitates multi-objective optimization, where operators must balance trade-offs between multiple objectives simultaneously, often using limited, temporally expensive beam observations. Usually, accelerator optimization problems are solved offline, prior to actual operation, with advanced beamline simulations and parallelized optimization methods (NSGA-II, Swarm Optimization). Unfortunately, it is not feasible to use these methods for online multi-objective optimization, since beam measurements can only be done in a serial fashion, and these optimization methods require a large number of measurements to converge to a useful solution.Here, we introduce a multi-objective Bayesian optimization scheme, which finds the full Pareto front of an accelerator optimization problem efficiently in a serialized manner and is thus a critical step towards practical online multi-objective optimization in accelerators.This method uses a set of Gaussian process surrogate models, along with a multi-objective acquisition function, which reduces the number of observations needed to converge by at least an order of magnitude over current methods.We demonstrate how this method can be modified to specifically solve optimization challenges posed by the tuning of accelerators.This includes the addition of optimization constraints, objective preferences and costs related to changing accelerator parameters.