CBOL-Tuner: Classifier-pruned Bayesian optimization to explore temporally structured latent spaces for particle accelerator tuning
This work addresses the time-consuming tuning procedures for complex dynamical systems like particle accelerators, offering a more efficient solution for researchers and engineers in physics and engineering.
The paper tackles the high-dimensional optimization problem of tuning particle accelerators for optimal performance by proposing CBOL-Tuner, a framework that integrates multiple neural networks and Bayesian optimization to explore latent spaces, resulting in superior performance in identifying optimal settings compared to alternative methods.
Complex dynamical systems, such as particle accelerators, often require complicated and time-consuming tuning procedures for optimal performance. It may also be required that these procedures estimate the optimal system parameters, which govern the dynamics of a spatiotemporal beam -- this can be a high-dimensional optimization problem. To address this, we propose a Classifier-pruned Bayesian Optimization-based Latent space Tuner (CBOL-Tuner), a framework for efficient exploration within a temporally-structured latent space. The CBOL-Tuner integrates a convolutional variational autoencoder (CVAE) for latent space representation, a long short-term memory (LSTM) network for temporal dynamics, a dense neural network (DNN) for parameter estimation, and a classifier-pruned Bayesian optimizer (C-BO) to adaptively search and filter the latent space for optimal solutions. CBOL-Tuner demonstrates superior performance in identifying multiple optimal settings and outperforms alternative global optimization methods.