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

TL;DR

This paper introduces an adaptive machine learning method that maps high-dimensional inputs to a low-dimensional latent space, enabling real-time tuning and tracking of time-varying systems like particle accelerators without extensive retraining.

Contribution

The novel approach maps high-dimensional data into a low-dimensional latent space and actively tunes it with feedback, facilitating real-time adaptation in complex, shifting systems.

Findings

Effective real-time tracking of system evolution.

Reduced need for extensive retraining data.

Successful application to particle accelerator systems.

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.