Double descent: When do neural quantum states generalize?
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866918390900195328 |
|---|---|
| author | Moss, M. Schuyler Orfi, Alev Roth, Christopher Sengupta, Anirvan M. Georges, Antoine Sels, Dries Dawid, Anna Valenti, Agnes |
| author_facet | Moss, M. Schuyler Orfi, Alev Roth, Christopher Sengupta, Anirvan M. Georges, Antoine Sels, Dries Dawid, Anna Valenti, Agnes |
| contents | Neural quantum states (NQS) provide flexible and compact wavefunction parameterizations for numerical studies of quantum many-body physics. In particular, NQS aim to circumvent the exponential scaling of the Hilbert space by compressing quantum many-body wavefunctions with a tractable amount of parameters. While inspired by deep learning, it remains unclear to what extent NQS share characteristics with neural networks used for standard machine learning tasks. We demonstrate that, in a simplified supervised setting, NQS exhibit the double descent phenomenon, a key feature of modern deep learning, where generalization worsens as network size increases before improving again in an overparameterized regime. Notably, we find the second descent to occur only for network sizes much larger than the Hilbert space dimension, i.e. network sizes that are out of reach for problems of practical interest. Within our setting, this observation places typical NQS in the underparameterized regime. We also observe that the optimal network size in the underparameterized regime depends on the number of unique training samples. While the double descent phenomenon does indeed translate to the NQS setting, potential practical consequences of our findings point more towards the need for symmetry-aware, physics-informed architecture design, rather than directly adopting machine learning heuristics. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_00068 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Double descent: When do neural quantum states generalize? Moss, M. Schuyler Orfi, Alev Roth, Christopher Sengupta, Anirvan M. Georges, Antoine Sels, Dries Dawid, Anna Valenti, Agnes Disordered Systems and Neural Networks Quantum Physics Neural quantum states (NQS) provide flexible and compact wavefunction parameterizations for numerical studies of quantum many-body physics. In particular, NQS aim to circumvent the exponential scaling of the Hilbert space by compressing quantum many-body wavefunctions with a tractable amount of parameters. While inspired by deep learning, it remains unclear to what extent NQS share characteristics with neural networks used for standard machine learning tasks. We demonstrate that, in a simplified supervised setting, NQS exhibit the double descent phenomenon, a key feature of modern deep learning, where generalization worsens as network size increases before improving again in an overparameterized regime. Notably, we find the second descent to occur only for network sizes much larger than the Hilbert space dimension, i.e. network sizes that are out of reach for problems of practical interest. Within our setting, this observation places typical NQS in the underparameterized regime. We also observe that the optimal network size in the underparameterized regime depends on the number of unique training samples. While the double descent phenomenon does indeed translate to the NQS setting, potential practical consequences of our findings point more towards the need for symmetry-aware, physics-informed architecture design, rather than directly adopting machine learning heuristics. |
| title | Double descent: When do neural quantum states generalize? |
| topic | Disordered Systems and Neural Networks Quantum Physics |
| url | https://arxiv.org/abs/2508.00068 |