CBOL-Tuner: Classifier-pruned Bayesian optimization to explore temporally structured latent spaces for particle accelerator tuning

TL;DR

CBOL-Tuner is a novel framework combining deep learning and Bayesian optimization to efficiently explore and optimize high-dimensional, temporally-structured latent spaces in complex dynamical systems like particle accelerators.

Contribution

It introduces a classifier-pruned Bayesian optimization approach integrated with deep neural networks for effective tuning of high-dimensional, temporally-structured systems.

Findings

Outperforms existing global optimization methods

Successfully identifies multiple optimal parameter settings

Demonstrates efficiency in complex dynamical system tuning

Abstract

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.