# Towards Accelerated SCF Workflows with Equivariant Density-Matrix Learning and Analytic Refinement

arXiv: https://arxiv.org/abs/2604.27256 · HTML: https://mlsanity.com/paper/2604.27256/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 2 of its 11 references that are in the map.
- First posted on arXiv 29 Apr 2026.

## Builds on (most cited first, 2 of 2)

- [MACE: Higher Order Equivariant Message Passing Neural Networks for Fast and Accurate Force Fields](https://mlsanity.com/paper/2206.07697/) (2022)
- [Delta-learned force fields for nonbonded interactions: Addressing the strength mismatch between covalent-nonbonded interaction for global models](https://mlsanity.com/paper/2511.01913/) (2025)

## Built on by (most cited first, 1 of 1)

- [Physics-Aligned Electronic Ground-State Learning Improves Generalization](https://mlsanity.com/paper/2610.10298/) (2026)

## Abstract (arXiv)

We present textscdm-PhiSNet, a physically constrained textscPhiSNet-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 L"owdin-orthogonalized density. Across six closed-shell systems -- H2O, CH4, NH3, HF, ethanol, and NO3^- -- 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.