Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2406.01552 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866918331488927744 |
|---|---|
| author | Gregory, Wilson G. Tonelli-Cueto, Josué Marshall, Nicholas F. Lee, Andrew S. Villar, Soledad |
| author_facet | Gregory, Wilson G. Tonelli-Cueto, Josué Marshall, Nicholas F. Lee, Andrew S. Villar, Soledad |
| contents | Tensors are a fundamental data structure for many scientific contexts, such as time series analysis, materials science, and physics, among many others. Improving our ability to produce and handle tensors is essential to efficiently address problems in these domains. In this paper, we show how to exploit the underlying symmetries of functions that map tensors to tensors. More concretely, we develop universally expressive equivariant machine learning architectures on tensors that exploit that, in many cases, these tensor functions are equivariant with respect to the diagonal action of the orthogonal, Lorentz, and/or symplectic groups. We showcase our results on three problems coming from material science, theoretical computer science, and time series analysis. For time series, we combine our method with the increasingly popular path signatures approach, which is also invariant with respect to reparameterizations. Our numerical experiments show that our equivariant models perform better than corresponding non-equivariant baselines. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2406_01552 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Tensor learning with orthogonal, Lorentz, and symplectic symmetries Gregory, Wilson G. Tonelli-Cueto, Josué Marshall, Nicholas F. Lee, Andrew S. Villar, Soledad Machine Learning Artificial Intelligence Tensors are a fundamental data structure for many scientific contexts, such as time series analysis, materials science, and physics, among many others. Improving our ability to produce and handle tensors is essential to efficiently address problems in these domains. In this paper, we show how to exploit the underlying symmetries of functions that map tensors to tensors. More concretely, we develop universally expressive equivariant machine learning architectures on tensors that exploit that, in many cases, these tensor functions are equivariant with respect to the diagonal action of the orthogonal, Lorentz, and/or symplectic groups. We showcase our results on three problems coming from material science, theoretical computer science, and time series analysis. For time series, we combine our method with the increasingly popular path signatures approach, which is also invariant with respect to reparameterizations. Our numerical experiments show that our equivariant models perform better than corresponding non-equivariant baselines. |
| title | Tensor learning with orthogonal, Lorentz, and symplectic symmetries |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2406.01552 |