mlsanityData to 7 Oct 2026

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

arXiv 2107.06207 ↗First posted 13 Jul 2021cs.LG physics.acc-ph stat.MLcited by 3

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 9 of its 53 references that are in the map. First posted on arXiv 13 Jul 2021.

Builds on

9 of 53 references.

References · 9

  1. 2016Variational Autoencoder for Deep Learning of Images, Labels and Captionscited by 137
  2. 2020Sample-Efficient Optimization in the Latent Space of Deep Generative Models via Weighted Retrainingcited by 121
  3. 2018Hamiltonian Variational Auto-Encodercited by 41
  4. 2020Model-free and Bayesian Ensembling Model-based Deep Reinforcement Learning for Particle Accelerator Control Demonstrated on the FERMI FELcited by 7
  5. 2021High-fidelity Prediction of Megapixel Longitudinal Phase-space Images of Electron Beams using Encoder-Decoder Neural Networkscited by 7
  6. 2021A Novel Approach for Classification and Forecasting of Time Series in Particle Acceleratorscited by 7
  7. 2020Accurate and confident prediction of electron beam longitudinal properties using spectral virtual diagnosticscited by 5
  8. 2019Online tuning and light source control using a physics-informed Gaussian process Adicited by 2
  9. 2021Adaptive Latent Space Tuning for Non-Stationary Distributionscited by 1

Built on by

Cited by year

Citing papers per year: 2023: 1; 2024: 2.

3 papers.

  1. 2024A conditional latent autoregressive recurrent model for generation and forecasting of beam dynamics in particle acceleratorscited by 7
  2. 2024Dynamical system prediction from sparse observations using deep neural networks with Voronoi tessellation and physics constraintcited by 5
  3. 2023Physics-constrained 3D Convolutional Neural Networks for Electrodynamicscited by 3