Adiabatic Fine-Tuning of Neural Quantum States Enables Detection of Phase Transitions in Weight Space
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_ | 1866915249676877824 |
|---|---|
| author | Hernandes, Vinicius Spriggs, Thomas Khaleefah, Saqar Greplova, Eliska |
| author_facet | Hernandes, Vinicius Spriggs, Thomas Khaleefah, Saqar Greplova, Eliska |
| contents | Neural quantum states (NQS) have emerged as a powerful tool for approximating quantum wavefunctions using deep learning. While these models achieve remarkable accuracy, understanding how they encode physical information remains an open challenge. In this work, we introduce adiabatic fine-tuning, a scheme that trains NQS across a phase diagram, leading to strongly correlated weight representations across different models. This correlation in weight space enables the detection of phase transitions in quantum systems by analyzing the trained network weights alone. We validate our approach on the transverse field Ising model and the J1-J2 Heisenberg model, demonstrating that phase transitions manifest as distinct structures in weight space. Our results establish a connection between physical phase transitions and the geometry of neural network parameters, opening new directions for the interpretability of machine learning models in physics. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_17140 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Adiabatic Fine-Tuning of Neural Quantum States Enables Detection of Phase Transitions in Weight Space Hernandes, Vinicius Spriggs, Thomas Khaleefah, Saqar Greplova, Eliska Quantum Physics Machine Learning Neural quantum states (NQS) have emerged as a powerful tool for approximating quantum wavefunctions using deep learning. While these models achieve remarkable accuracy, understanding how they encode physical information remains an open challenge. In this work, we introduce adiabatic fine-tuning, a scheme that trains NQS across a phase diagram, leading to strongly correlated weight representations across different models. This correlation in weight space enables the detection of phase transitions in quantum systems by analyzing the trained network weights alone. We validate our approach on the transverse field Ising model and the J1-J2 Heisenberg model, demonstrating that phase transitions manifest as distinct structures in weight space. Our results establish a connection between physical phase transitions and the geometry of neural network parameters, opening new directions for the interpretability of machine learning models in physics. |
| title | Adiabatic Fine-Tuning of Neural Quantum States Enables Detection of Phase Transitions in Weight Space |
| topic | Quantum Physics Machine Learning |
| url | https://arxiv.org/abs/2503.17140 |