Adaptive Machine Learning for Time-Varying Systems: Low Dimensional Latent Space Tuning

Abstract

Machine learning (ML) tools such as encoder-decoder convolutional neural networks (CNN) can represent incredibly complex nonlinear functions which map between combinations of images and scalars. For example, CNNs can be used to map combinations of accelerator parameters and images which are 2D projections of the 6D phase space distributions of charged particle beams as they are transported between various particle accelerator locations. Despite their strengths, applying ML to time-varying systems, or systems with shifting distributions, is an open problem, especially for large systems for which collecting new data for re-training is impractical or interrupts operations. Particle accelerators are one example of large time-varying systems for which collecting detailed training data requires lengthy dedicated beam measurements which may no longer be available during regular operations. We present a recently developed method of adaptive ML for time-varying systems. Our approach is to map very high (N>100k) dimensional inputs (a combination of scalar parameters and images) into the low dimensional (N~2) latent space at the output of the encoder section of an encoder-decoder CNN. We then actively tune the low dimensional latent space-based representation of complex system dynamics by the addition of an adaptively tuned feedback vector directly before the decoder sections builds back up to our image-based high-dimensional phase space density representations. This method allows us to learn correlations within and to quickly tune the characteristics of incredibly high parameter systems and to track their evolution in real time based on feedback without massive new data sets for re-training.

References in corpus (18)

• Acceleration of electrons in the plasma wakefield of a proton bunch
• Bayesian optimization of a free-electron laser
• Automation and control of laser wakefield accelerators using Bayesian optimisation
• Time-series learning of latent-space dynamics for reduced-order model closure
• Machine Learning for Orders of Magnitude Speedup in Multi-Objective Optimization of Particle Accelerator Systems
• Multi-Objective Bayesian Optimization for Accelerator Tuning
• Machine learning for beam dynamics studies at the CERN Large Hadron Collider
• Multiobjective optimization of the dynamic aperture for SLS 2.0 using surrogate models based on artificial neural networks
• High-fidelity Prediction of Megapixel Longitudinal Phase-space Images of Electron Beams using Encoder-Decoder Neural Networks
• Accurate and confident prediction of electron beam longitudinal properties using spectral virtual diagnostics
• Uncertainty Quantification for Virtual Diagnostic of Particle Accelerators
• A Novel Approach for Classification and Forecasting of Time Series in Particle Accelerators
• Analysis of beam position monitor requirements with Bayesian Gaussian regression
• Reconstruction of Storage Ring 's Linear Optics with Bayesian Inference
• Bayesian Approach for Linear Optics Correction
• Model-free and Bayesian Ensembling Model-based Deep Reinforcement Learning for Particle Accelerator Control Demonstrated on the FERMI FEL
• Improving Surrogate Model Accuracy for the LCLS-II Injector Frontend Using Convolutional Neural Networks and Transfer Learning
• Online tuning and light source control using a physics-informed Gaussian process Adi

Cited by in corpus (3)

• 2022 Review of Data-Driven Plasma Science
• Transverse phase space tomography in the CLARA accelerator test facility using image compression and machine learning
• Uncertainty Aware ML-based surrogate models for particle accelerators: A Study at the Fermilab Booster Accelerator Complex