MLLGACC-PHMay 8, 2021

Adaptive Latent Space Tuning for Non-Stationary Distributions

arXiv:2105.03584v42 citations
Originality Incremental advance
AI Analysis

This addresses the problem of non-stationary distributions in deep learning for real-time applications like particle accelerators, but it is incremental as it builds on existing encoder-decoder CNN frameworks.

The paper tackles the challenge of predicting properties in time-varying systems with fast distribution shifts, such as a particle accelerator's charged particle beam, by introducing an adaptive tuning method for the latent space of encoder-decoder CNNs, achieving real-time compensation without retraining.

Powerful deep learning tools, such as convolutional neural networks (CNN), are able to learn the input-output relationships of large complicated systems directly from data. Encoder-decoder deep CNNs are able to extract features directly from images, mix them with scalar inputs within a general low-dimensional latent space, and then generate new complex 2D outputs which represent complex physical phenomenon. One important challenge faced by deep learning methods is large non-stationary systems whose characteristics change quickly with time for which re-training is not feasible. In this paper we present a method for adaptive tuning of the low-dimensional latent space of deep encoder-decoder style CNNs based on real-time feedback to quickly compensate for unknown and fast distribution shifts. We demonstrate our approach for predicting the properties of a time-varying charged particle beam in a particle accelerator whose components (accelerating electric fields and focusing magnetic fields) are also quickly changing with time.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes