# Continual learning autoencoder training for a particle-in-cell simulation via streaming

arXiv: https://arxiv.org/abs/2211.04770 · HTML: https://mlsanity.com/paper/2211.04770/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 7 of its 11 references that are in the map.
- First posted on arXiv 9 Nov 2022.

## Builds on (most cited first, 7 of 7)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Overcoming catastrophic forgetting in neural networks](https://mlsanity.com/paper/1612.00796/) (2016)
- [Deep Fluids: A Generative Network for Parameterized Fluid Simulations](https://mlsanity.com/paper/1806.02071/) (2018)
- [Understanding SSIM](https://mlsanity.com/paper/2006.13846/) (2020)
- [Large-scale Neural Solvers for Partial Differential Equations](https://mlsanity.com/paper/2009.03730/) (2020)
- [Data-Driven Shadowgraph Simulation of a 3D Object](https://mlsanity.com/paper/2106.00317/) (2021)
- [Invertible Surrogate Models: Joint surrogate modelling and reconstruction of Laser-Wakefield Acceleration by invertible neural networks](https://mlsanity.com/paper/2106.00432/) (2021)

## Built on by (most cited first, 2 of 2)

- [Training Deep Surrogate Models with Large Scale Online Learning](https://mlsanity.com/paper/2306.16133/) (2023)
- [Data-driven Science and Machine Learning Methods in Laser-Plasma Physics](https://mlsanity.com/paper/2212.00026/) (2022)

## Abstract (arXiv)

The upcoming exascale era will provide a new generation of physics simulations. These simulations will have a high spatiotemporal resolution, which will impact the training of machine learning models since storing a high amount of simulation data on disk is nearly impossible. Therefore, we need to rethink the training of machine learning models for simulations for the upcoming exascale era. This work presents an approach that trains a neural network concurrently to a running simulation without storing data on a disk. The training pipeline accesses the training data by in-memory streaming. Furthermore, we apply methods from the domain of continual learning to enhance the generalization of the model. We tested our pipeline on the training of a 3d autoencoder trained concurrently to laser wakefield acceleration particle-in-cell simulation. Furthermore, we experimented with various continual learning methods and their effect on the generalization.