Prior-mean-assisted Bayesian optimization application on FRIB Front-End tunning
This work addresses computational bottlenecks in accelerator tuning for researchers and engineers, but it is incremental as it builds on existing Bayesian optimization methods.
The paper tackled the computational scalability and historical data integration challenges in Bayesian optimization for accelerator tuning by using a neural network trained on historical data as a prior mean, resulting in improved tuning efficiency for the FRIB Front-End.
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.