Guardado en:
Detalles Bibliográficos
Autores principales: Dymchenko, Sofya, Purandare, Abhishek, Raffin, Bruno
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:https://arxiv.org/abs/2410.05860
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866913537616510976
author Dymchenko, Sofya
Purandare, Abhishek
Raffin, Bruno
author_facet Dymchenko, Sofya
Purandare, Abhishek
Raffin, Bruno
contents Artificial intelligence is transforming scientific computing with deep neural network surrogates that approximate solutions to partial differential equations (PDEs). Traditional off-line training methods face issues with storage and I/O efficiency, as the training dataset has to be computed with numerical solvers up-front. Our previous work, the Melissa framework, addresses these problems by enabling data to be created "on-the-fly" and streamed directly into the training process. In this paper we introduce a new active learning method to enhance data-efficiency for on-line surrogate training. The surrogate is direct and multi-parametric, i.e., it is trained to predict a given timestep directly with different initial and boundary conditions parameters. Our approach uses Adaptive Multiple Importance Sampling guided by training loss statistics, in order to focus NN training on the difficult areas of the parameter space. Preliminary results for 2D heat PDE demonstrate the potential of this method, called Breed, to improve the generalization capabilities of surrogates while reducing computational overhead.
format Preprint
id arxiv_https___arxiv_org_abs_2410_05860
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle MelissaDL x Breed: Towards Data-Efficient On-line Supervised Training of Multi-parametric Surrogates with Active Learning
Dymchenko, Sofya
Purandare, Abhishek
Raffin, Bruno
Machine Learning
Artificial Intelligence
Artificial intelligence is transforming scientific computing with deep neural network surrogates that approximate solutions to partial differential equations (PDEs). Traditional off-line training methods face issues with storage and I/O efficiency, as the training dataset has to be computed with numerical solvers up-front. Our previous work, the Melissa framework, addresses these problems by enabling data to be created "on-the-fly" and streamed directly into the training process. In this paper we introduce a new active learning method to enhance data-efficiency for on-line surrogate training. The surrogate is direct and multi-parametric, i.e., it is trained to predict a given timestep directly with different initial and boundary conditions parameters. Our approach uses Adaptive Multiple Importance Sampling guided by training loss statistics, in order to focus NN training on the difficult areas of the parameter space. Preliminary results for 2D heat PDE demonstrate the potential of this method, called Breed, to improve the generalization capabilities of surrogates while reducing computational overhead.
title MelissaDL x Breed: Towards Data-Efficient On-line Supervised Training of Multi-parametric Surrogates with Active Learning
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2410.05860