Prior-mean-assisted Bayesian optimization application on FRIB Front-End tunning

TL;DR

This paper introduces a method that uses a neural network trained on historical data as a prior mean in Bayesian optimization to improve the efficiency of tuning the FRIB Front-End, addressing scalability issues.

Contribution

The paper proposes a novel approach combining neural network priors with Bayesian optimization for accelerator tuning, enhancing scalability and efficiency.

Findings

Improved tuning efficiency for FRIB Front-End

Effective use of historical data in BO

Scalable approach for large datasets

Abstract

Bayesian optimization~(BO) is often used for accelerator tuning due to its high sample efficiency. However, the computational scalability of training over large data-set can be problematic and the adoption of historical data in a computationally efficient way is not trivial. Here, we exploit a neural network model trained over historical data as a prior mean of BO for FRIB Front-End tuning.