Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2505.18671 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915303380746240 |
|---|---|
| author | Turri, Giacomo Bonati, Luigi Zhu, Kai Pontil, Massimiliano Novelli, Pietro |
| author_facet | Turri, Giacomo Bonati, Luigi Zhu, Kai Pontil, Massimiliano Novelli, Pietro |
| contents | We introduce an encoder-only approach to learn the evolution operators of large-scale non-linear dynamical systems, such as those describing complex natural phenomena. Evolution operators are particularly well-suited for analyzing systems that exhibit complex spatio-temporal patterns and have become a key analytical tool across various scientific communities. As terabyte-scale weather datasets and simulation tools capable of running millions of molecular dynamics steps per day are becoming commodities, our approach provides an effective tool to make sense of them from a data-driven perspective. The core of it lies in a remarkable connection between self-supervised representation learning methods and the recently established learning theory of evolution operators. To show the usefulness of the proposed method, we test it across multiple scientific domains: explaining the folding dynamics of small proteins, the binding process of drug-like molecules in host sites, and autonomously finding patterns in climate data. Code and data to reproduce the experiments are made available open source. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_18671 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Self-Supervised Evolution Operator Learning for High-Dimensional Dynamical Systems Turri, Giacomo Bonati, Luigi Zhu, Kai Pontil, Massimiliano Novelli, Pietro Machine Learning Dynamical Systems We introduce an encoder-only approach to learn the evolution operators of large-scale non-linear dynamical systems, such as those describing complex natural phenomena. Evolution operators are particularly well-suited for analyzing systems that exhibit complex spatio-temporal patterns and have become a key analytical tool across various scientific communities. As terabyte-scale weather datasets and simulation tools capable of running millions of molecular dynamics steps per day are becoming commodities, our approach provides an effective tool to make sense of them from a data-driven perspective. The core of it lies in a remarkable connection between self-supervised representation learning methods and the recently established learning theory of evolution operators. To show the usefulness of the proposed method, we test it across multiple scientific domains: explaining the folding dynamics of small proteins, the binding process of drug-like molecules in host sites, and autonomously finding patterns in climate data. Code and data to reproduce the experiments are made available open source. |
| title | Self-Supervised Evolution Operator Learning for High-Dimensional Dynamical Systems |
| topic | Machine Learning Dynamical Systems |
| url | https://arxiv.org/abs/2505.18671 |