English

DISCO: learning to DISCover an evolution Operator for multi-physics-agnostic prediction

Machine Learning 2025-04-29 v1 Artificial Intelligence Machine Learning

Abstract

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.

Keywords

Cite

@article{arxiv.2504.19496,
  title  = {DISCO: learning to DISCover an evolution Operator for multi-physics-agnostic prediction},
  author = {Rudy Morel and Jiequn Han and Edouard Oyallon},
  journal= {arXiv preprint arXiv:2504.19496},
  year   = {2025}
}
R2 v1 2026-06-28T23:13:18.882Z