Machine learning mapping of lattice correlated data
Fuente:
arXiv
Salvato in:
| Autori principali: | , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866916375829676032 |
|---|---|
| author | Kim, Jangho Pederiva, Giovanni Shindler, Andrea |
| author_facet | Kim, Jangho Pederiva, Giovanni Shindler, Andrea |
| contents | We discuss a machine learning (ML) regression model to reduce the computational cost of disconnected diagrams in lattice QCD calculations. This method creates a mapping between the results of fermionic loops computed at different quark masses and flow times. The ML mapping, trained with just a small fraction of the complete data set, makes use of translational invariance and provides consistent result with comparable uncertainties over the calculation done over the whole ensemble, resulting in a significant computational gain. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2402_07450 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Machine learning mapping of lattice correlated data Kim, Jangho Pederiva, Giovanni Shindler, Andrea High Energy Physics - Lattice We discuss a machine learning (ML) regression model to reduce the computational cost of disconnected diagrams in lattice QCD calculations. This method creates a mapping between the results of fermionic loops computed at different quark masses and flow times. The ML mapping, trained with just a small fraction of the complete data set, makes use of translational invariance and provides consistent result with comparable uncertainties over the calculation done over the whole ensemble, resulting in a significant computational gain. |
| title | Machine learning mapping of lattice correlated data |
| topic | High Energy Physics - Lattice |
| url | https://arxiv.org/abs/2402.07450 |