Salvato in:
| Autori principali: | , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | https://arxiv.org/abs/2510.01328 |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866911190240722944 |
|---|---|
| author | Aarts, Gert Habibi, Diaa E. Wang, Lingxiao Zhou, Kai |
| author_facet | Aarts, Gert Habibi, Diaa E. Wang, Lingxiao Zhou, Kai |
| contents | Theories with a sign problem due to a complex action or Boltzmann weight can sometimes be numerically solved using a stochastic process in the complexified configuration space. However, the probability distribution effectively sampled by this complex Langevin process is not known a priori and notoriously hard to understand. In generative AI, diffusion models can learn distributions, or their log derivatives, from data. We explore the ability of diffusion models to learn the distributions sampled by a complex Langevin process, comparing score-based and energy-based diffusion models, and speculate about possible applications. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_01328 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Combining complex Langevin dynamics with score-based and energy-based diffusion models Aarts, Gert Habibi, Diaa E. Wang, Lingxiao Zhou, Kai High Energy Physics - Lattice Disordered Systems and Neural Networks Machine Learning Theories with a sign problem due to a complex action or Boltzmann weight can sometimes be numerically solved using a stochastic process in the complexified configuration space. However, the probability distribution effectively sampled by this complex Langevin process is not known a priori and notoriously hard to understand. In generative AI, diffusion models can learn distributions, or their log derivatives, from data. We explore the ability of diffusion models to learn the distributions sampled by a complex Langevin process, comparing score-based and energy-based diffusion models, and speculate about possible applications. |
| title | Combining complex Langevin dynamics with score-based and energy-based diffusion models |
| topic | High Energy Physics - Lattice Disordered Systems and Neural Networks Machine Learning |
| url | https://arxiv.org/abs/2510.01328 |