# Classifier-pruned Bayesian optimization for particle accelerator tuning: Exploring temporally structured manifold of 6D beam phase space

arXiv: https://arxiv.org/abs/2412.01748 · HTML: https://mlsanity.com/paper/2412.01748/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 8 of its 30 references that are in the map.
- First posted on arXiv 2 Dec 2024.

## Builds on (most cited first, 8 of 8)

- [A Tutorial on Learning With Bayesian Networks](https://mlsanity.com/paper/2002.00269/) (2020)
- [An invertible crystallographic representation for general inverse design of inorganic crystals with targeted properties](https://mlsanity.com/paper/2005.07609/) (2020)
- [A conditional latent autoregressive recurrent model for generation and forecasting of beam dynamics in particle accelerators](https://mlsanity.com/paper/2403.13858/) (2024)
- [Tuning Particle Accelerators with Safety Constraints using Bayesian Optimization](https://mlsanity.com/paper/2203.13968/) (2022)
- [Time-inversion of spatiotemporal beam dynamics using uncertainty-aware latent evolution reversal](https://mlsanity.com/paper/2408.07847/) (2024)
- [Experimental Safe Extremum Seeking for Accelerators](https://mlsanity.com/paper/2308.15584/) (2023)
- [Prior-mean-assisted Bayesian optimization application on FRIB Front-End tunning](https://mlsanity.com/paper/2211.06400/) (2022)
- [cDVAE: Multimodal Generative Conditional Diffusion Guided by Variational Autoencoder Latent Embedding for Virtual 6D Phase Space Diagnostics](https://mlsanity.com/paper/2407.20218/) (2024)

## Built on by (most cited first, 1 of 1)

- [Advancing accelerator virtual beam diagnostics through latent evolution modeling: an integrated solution to forward, inverse, tuning, and UQ problems](https://mlsanity.com/paper/2602.22618/) (2026)

## Abstract (arXiv)

Complex dynamical systems, such as particle accelerators, require tuning over high-dimensional, nonlinear state and parameter spaces while experimental measurements and high-fidelity simulations can be expensive. Learned latent representations provide a compact domain for such optimization, but poorly supported regions of the learned manifold may decode into unrealistic physical states and yield deceptively favorable objectives. To address this challenge, we propose the Classifier-pruned Bayesian Optimization-based Latent-space Tuner (CBOL-Tuner), which performs Bayesian optimization over a temporally structured latent representation of 6D beam phase-space dynamics. The CBOL-Tuner integrates a conditional variational autoencoder for latent space representation, a long short-term memory network for temporal dynamics, a lightweight neural network for parameter estimation, and a classifier-pruned Bayesian optimizer to adaptively search and filter the latent space for optimal solutions. This framework enables feasibility-aware exploration of learned scientific representations for accelerator tuning.