Towards Accelerated SCF Workflows with Equivariant Density-Matrix Learning and Analytic Refinement
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2026
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866910179373613056 |
|---|---|
| author | Yescas-Ramos, Zuriel Y. Álvarez-García, Andrés Sauceda, Huziel E. |
| author_facet | Yescas-Ramos, Zuriel Y. Álvarez-García, Andrés Sauceda, Huziel E. |
| contents | We present \textsc{dm-PhiSNet}, a physically constrained \textsc{PhiSNet}-based equivariant model that predicts one-electron reduced density matrices (1-RDMs) directly from molecular geometries in an atomic-orbital (AO) basis for accelerated self-consistent field (SCF) workflows. Training follows a two-stage schedule with progressively introduced physically motivated objectives, and the resulting predictions are refined by a lightweight analytic block. This block enforces electron-number conservation, drives the 1-RDM toward generalized idempotency in the AO metric, and regularizes the occupation spectrum of the Löwdin-orthogonalized density. Across six closed-shell systems -- H$_2$O, CH$_4$, NH$_3$, HF, ethanol, and NO$_3^-$ -- the refined 1-RDMs provide SCF initial guesses that substantially reduce iteration steps by 49--81\% relative to standard initializations. Beyond SCF acceleration, the learned 1-RDMs yield accurate one-shot total energies and Hellmann--Feynman atomic forces without force supervision, indicating that the model captures chemically meaningful electronic structure. These results demonstrate that combining equivariant learning with analytic constraint enforcement provides a simple, general route to solver-ready density-matrix initializations and accelerated SCF workflows. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_27256 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Towards Accelerated SCF Workflows with Equivariant Density-Matrix Learning and Analytic Refinement Yescas-Ramos, Zuriel Y. Álvarez-García, Andrés Sauceda, Huziel E. Chemical Physics Artificial Intelligence Machine Learning Computational Physics Quantum Physics We present \textsc{dm-PhiSNet}, a physically constrained \textsc{PhiSNet}-based equivariant model that predicts one-electron reduced density matrices (1-RDMs) directly from molecular geometries in an atomic-orbital (AO) basis for accelerated self-consistent field (SCF) workflows. Training follows a two-stage schedule with progressively introduced physically motivated objectives, and the resulting predictions are refined by a lightweight analytic block. This block enforces electron-number conservation, drives the 1-RDM toward generalized idempotency in the AO metric, and regularizes the occupation spectrum of the Löwdin-orthogonalized density. Across six closed-shell systems -- H$_2$O, CH$_4$, NH$_3$, HF, ethanol, and NO$_3^-$ -- the refined 1-RDMs provide SCF initial guesses that substantially reduce iteration steps by 49--81\% relative to standard initializations. Beyond SCF acceleration, the learned 1-RDMs yield accurate one-shot total energies and Hellmann--Feynman atomic forces without force supervision, indicating that the model captures chemically meaningful electronic structure. These results demonstrate that combining equivariant learning with analytic constraint enforcement provides a simple, general route to solver-ready density-matrix initializations and accelerated SCF workflows. |
| title | Towards Accelerated SCF Workflows with Equivariant Density-Matrix Learning and Analytic Refinement |
| topic | Chemical Physics Artificial Intelligence Machine Learning Computational Physics Quantum Physics |
| url | https://arxiv.org/abs/2604.27256 |