Saved in:
Bibliographic Details
Main Authors: Morel, Rudy, Han, Jiequn, Oyallon, Edouard
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2504.19496
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918001928830976
author Morel, Rudy
Han, Jiequn
Oyallon, Edouard
author_facet Morel, Rudy
Han, Jiequn
Oyallon, Edouard
contents We address the problem of predicting the next state of a dynamical system governed by unknown temporal partial differential equations (PDEs) using only a short trajectory. While standard transformers provide a natural black-box solution to this task, the presence of a well-structured evolution operator in the data suggests a more tailored and efficient approach. Specifically, when the PDE is fully known, classical numerical solvers can evolve the state accurately with only a few parameters. Building on this observation, we introduce DISCO, a model that uses a large hypernetwork to process a short trajectory and generate the parameters of a much smaller operator network, which then predicts the next state through time integration. Our framework decouples dynamics estimation (i.e., DISCovering an evolution operator from a short trajectory) from state prediction (i.e., evolving this operator). Experiments show that pretraining our model on diverse physics datasets achieves state-of-the-art performance while requiring significantly fewer epochs. Moreover, it generalizes well and remains competitive when fine-tuned on downstream tasks.
format Preprint
id arxiv_https___arxiv_org_abs_2504_19496
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle DISCO: learning to DISCover an evolution Operator for multi-physics-agnostic prediction
Morel, Rudy
Han, Jiequn
Oyallon, Edouard
Machine Learning
Artificial Intelligence
We address the problem of predicting the next state of a dynamical system governed by unknown temporal partial differential equations (PDEs) using only a short trajectory. While standard transformers provide a natural black-box solution to this task, the presence of a well-structured evolution operator in the data suggests a more tailored and efficient approach. Specifically, when the PDE is fully known, classical numerical solvers can evolve the state accurately with only a few parameters. Building on this observation, we introduce DISCO, a model that uses a large hypernetwork to process a short trajectory and generate the parameters of a much smaller operator network, which then predicts the next state through time integration. Our framework decouples dynamics estimation (i.e., DISCovering an evolution operator from a short trajectory) from state prediction (i.e., evolving this operator). Experiments show that pretraining our model on diverse physics datasets achieves state-of-the-art performance while requiring significantly fewer epochs. Moreover, it generalizes well and remains competitive when fine-tuned on downstream tasks.
title DISCO: learning to DISCover an evolution Operator for multi-physics-agnostic prediction
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2504.19496