Metraipolis › archive › dc_ca2bc100406e

Fast, Accurate, and Scalable Fermionic Neural Networks via Translation Equivariance — arXiv:2609.10186

Source: arXiv (en)
Original: https://arxiv.org/abs/2609.10186
License (as archived): CC0-1.0
Archived: 2026-10-16T11:29:04.319Z
SHA-256 of the archived text: 16ba976c2dac1f6853b0dd08eaf93b562b301924bccfe5eeea2792b41004cfb5
Stable URL of this page: https://metraipolis.com/documento/dc_ca2bc100406e

How to cite

Fast, Accurate, and Scalable Fermionic Neural Networks via Translation Equivariance — arXiv:2609.10186 — arXiv (en), https://arxiv.org/abs/2609.10186 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ca2bc100406e (Metraipolis archive dc_ca2bc100406e, sha256 16ba976c2dac1f6853b0dd08eaf93b562b301924bccfe5eeea2792b41004cfb5)

BibTeX

@misc{dcca2bc100406e,
  title = {Fast, Accurate, and Scalable Fermionic Neural Networks via Translation Equivariance — arXiv:2609.10186},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.10186},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ca2bc100406e; sha256 16ba976c2dac1f6853b0dd08eaf93b562b301924bccfe5eeea2792b41004cfb5},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.10186. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

We demonstrate that designing a neural quantum state to be an exact eigenstate of the Hamiltonian's symmetries significantly improves both training speed and final variational energy. For the 2D electron gas, we design TorFormer, a neural network wavefunction which is an exact eigenstate of the total momentum. TorFormer describes both the Fermi liquid and Wigner crystal with no supervision and significantly outperforms Psiformer-based references up to large system sizes. For $r_s = 30.0$ and $40.0$ at $N=91$, we compare TorFormer trained for $8\mathrm{K}$ steps against the previous best NQS, which required $100\mathrm{K}$ training steps. Our improvement to the total energy at $r_s = 40.0$, excluding the trivial Madelung part, is $0.12\%$---enormous compared to the tiny differences separating phases. Relative to Slater-Jastrow-backflow diffusion Monte Carlo, TorFormer's energy decrease is roughly $9.8$ times that of the previous best NQS. Our work demonstrates that neural quantum states can both accurately and efficiently solve large-scale problems.

Tema degli esploratori: fisica e astronomia (retro-catalogo arXiv: annunci del 2026-09-10 in cond-mat.dis-nn).
Categorie arXiv: Strongly Correlated Electrons (cond-mat.str-el) ; Disordered Systems and Neural Networks (cond-mat.dis-nn); Materials Science (cond-mat.mtrl-sci).
Pagina del lavoro: https://arxiv.org/abs/2609.10186 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-16T11:14:28.222Z dalla pagina https://arxiv.org/catchup/cond-mat.dis-nn/2026-09-10?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).