Is attention all you need to solve the correlated electron problem?
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866915387413626880 |
|---|---|
| author | Geier, Max Nazaryan, Khachatur Zaklama, Timothy Fu, Liang |
| author_facet | Geier, Max Nazaryan, Khachatur Zaklama, Timothy Fu, Liang |
| contents | The attention mechanism has transformed artificial intelligence research by its ability to learn relations between objects. In this work, we explore how a many-body wavefunction ansatz constructed from a large-parameter self-attention neural network can be used to solve the interacting electron problem in solids. By a systematic neural-network variational Monte Carlo study on a moiré quantum material, we demonstrate that the self-attention ansatz provides an accurate and efficient solution without human bias. Moreover, our numerical study finds that the required number of variational parameters scales roughly as $N^2$ with the number of electrons, which opens a path towards efficient large-scale simulations. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_05383 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Is attention all you need to solve the correlated electron problem? Geier, Max Nazaryan, Khachatur Zaklama, Timothy Fu, Liang Strongly Correlated Electrons Mesoscale and Nanoscale Physics Artificial Intelligence The attention mechanism has transformed artificial intelligence research by its ability to learn relations between objects. In this work, we explore how a many-body wavefunction ansatz constructed from a large-parameter self-attention neural network can be used to solve the interacting electron problem in solids. By a systematic neural-network variational Monte Carlo study on a moiré quantum material, we demonstrate that the self-attention ansatz provides an accurate and efficient solution without human bias. Moreover, our numerical study finds that the required number of variational parameters scales roughly as $N^2$ with the number of electrons, which opens a path towards efficient large-scale simulations. |
| title | Is attention all you need to solve the correlated electron problem? |
| topic | Strongly Correlated Electrons Mesoscale and Nanoscale Physics Artificial Intelligence |
| url | https://arxiv.org/abs/2502.05383 |