Advantages of density in tensor network geometries for gradient based training
Fuente:
arXiv
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909439067422720 |
|---|---|
| author | Masot-Llima, Sergi Garcia-Saez, Artur |
| author_facet | Masot-Llima, Sergi Garcia-Saez, Artur |
| contents | Tensor networks are a very powerful data structure tool originating from quantum system simulations. In recent years, they have seen increased use in machine learning, mostly in trainings with gradient-based techniques, due to their flexibility and performance exploiting hardware acceleration. As ansätze, tensor networks can be used with flexible geometries, and it is known that for highly regular ones their dimensionality has a large impact in performance and representation power. For heterogeneous structures, however, these effects are not completely characterized. In this article, we train tensor networks with different geometries to encode a random quantum state, and see that densely connected structures achieve better infidelities than more sparse structures, with higher success rates and less time. Additionally, we give some general insight on how to improve memory requirements on these sparse structures and its impact on the trainings. Finally, as we use HPC resources for the calculations, we discuss the requirements for this approach and showcase performance improvements with GPU acceleration on a last-generation supercomputer. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2412_17497 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Advantages of density in tensor network geometries for gradient based training Masot-Llima, Sergi Garcia-Saez, Artur Quantum Physics Tensor networks are a very powerful data structure tool originating from quantum system simulations. In recent years, they have seen increased use in machine learning, mostly in trainings with gradient-based techniques, due to their flexibility and performance exploiting hardware acceleration. As ansätze, tensor networks can be used with flexible geometries, and it is known that for highly regular ones their dimensionality has a large impact in performance and representation power. For heterogeneous structures, however, these effects are not completely characterized. In this article, we train tensor networks with different geometries to encode a random quantum state, and see that densely connected structures achieve better infidelities than more sparse structures, with higher success rates and less time. Additionally, we give some general insight on how to improve memory requirements on these sparse structures and its impact on the trainings. Finally, as we use HPC resources for the calculations, we discuss the requirements for this approach and showcase performance improvements with GPU acceleration on a last-generation supercomputer. |
| title | Advantages of density in tensor network geometries for gradient based training |
| topic | Quantum Physics |
| url | https://arxiv.org/abs/2412.17497 |