Turn-Key Constrained Parameter Space Exploration for Particle Accelerators Using Bayesian Active Learning

TL;DR

This paper introduces a Bayesian active learning algorithm that efficiently explores high-dimensional, constrained parameter spaces in particle accelerators, reducing the need for extensive prior knowledge and enabling autonomous experimentation.

Contribution

The work adapts Bayesian optimization for turn-key, constrained parameter exploration, improving upon traditional grid scans in accelerator experiments.

Findings

Successfully demonstrated autonomous multi-parameter exploration

Effectively navigated complex measurement constraints

Reduced prior information requirements

Abstract

Particle accelerators are invaluable discovery engines in the chemical, biological and physical sciences. Characterization of the accelerated beam response to accelerator input parameters is of-ten the first step when conducting accelerator-based experiments. Currently used techniques for characterization, such as grid-like parameter sampling scans, become impractical when extended to higher dimensional input spaces, when complicated measurement constraints are present, or prior information is known about the beam response is scarce. In this work, we describe an adaptation of the popular Bayesian optimization algorithm, which enables a turn-key exploration algorithm that replaces parameter scans and minimizes prior information needed about the measurements' behavior and associated measurement constraints. We experimentally demonstrate that our algorithm autonomously conducts an adaptive, multi-parameter exploration of input parameter space,while navigating a highly constrained, single-shot beam phase-space measurement. In addition to applications in accelerator-based scientific experiments, this algorithm addresses challenges shared by many scientific disciplines and is thus applicable to autonomously conducting experiments over a broad range of research topics.