الملخص
Machine-learned interatomic potentials (MLIPs) excel at in-distribution tasks, accelerating drug and material development, yet they struggle to generalize out-of-distribution. We propose to push the cost-accuracy Pareto frontier by designing observable-agnostic electronic ground-state descriptor models (GSMs) with computational costs situated between MLIPs and Kohn-Sham density functional theory (KS-DFT). We align the learning objectives and architectures of GSMs with the governing equations of KS-DFT by enforcing physical constraints and removing optimization pressure on unphysical or irrelevant degrees of freedom. In our size-extrapolation experiments from QM9 to QM40, our combined contributions OrthoNormal-Loss (ON-Loss) and Grassmann Restricted Occupied-Orbital Training (GROOT) reach a 79.1% energy and 83.4% force mean absolute error (MAE) reduction over previous state-of-the-art density GSMs. For Hamiltonian GSMs, ON-Loss and Residual Optimal-gauge Conditioning-aware KS-Eq. Training (ROCKET) together reduce the energy and force MAEs of the strongest baseline by 99.8% and 95.9%, respectively. Using a self-consistency rejection criterion, we filter out extrapolation errors on QMugs, rejecting fewer than 0.4% of predictions while reaching an energy MAE of 0.07 mHa. Finally, we demonstrate the efficiency of label-free self-consistency fine-tuning, and transfer GSMs to reactive chemistry in Transition1x, reaching energy errors below chemical accuracy.
الكلمات المفتاحية
الموضوع
بيانات النشر
- المجلة
- غير متاح
- وصول مفتوح
- وصول مفتوح أخضر
اقتبس هذه المقالة
APA 7
Eberhard, E. S., Kainz, X., Kotsev, V., Aldossary, A., & Günnemann, S. (2026). Physics-Aligned Electronic Ground-State Learning Improves Generalization. https://omanscience.com/ar/articles/physics-aligned-electronic-ground-state-learning-improves-generalization
MLA 9
Eberhard, Eike S., et al. "Physics-Aligned Electronic Ground-State Learning Improves Generalization." https://omanscience.com/ar/articles/physics-aligned-electronic-ground-state-learning-improves-generalization.
شيكاغو (المؤلف–التاريخ)
Eberhard, Eike S., Xaver Kainz, Viktor Kotsev, Abdulrahman Aldossary, and Stephan Günnemann. 2026. "Physics-Aligned Electronic Ground-State Learning Improves Generalization." https://omanscience.com/ar/articles/physics-aligned-electronic-ground-state-learning-improves-generalization.
هارفارد
Eberhard, E. S., Kainz, X., Kotsev, V., Aldossary, A. and Günnemann, S. (2026) 'Physics-Aligned Electronic Ground-State Learning Improves Generalization', Available at: https://omanscience.com/ar/articles/physics-aligned-electronic-ground-state-learning-improves-generalization.
فانكوفر
Eberhard ES, Kainz X, Kotsev V, Aldossary A, Günnemann S. Physics-Aligned Electronic Ground-State Learning Improves Generalization. https://omanscience.com/ar/articles/physics-aligned-electronic-ground-state-learning-improves-generalization
IEEE
E. S. Eberhard, X. Kainz, V. Kotsev, A. Aldossary, and S. Günnemann, "Physics-Aligned Electronic Ground-State Learning Improves Generalization," https://omanscience.com/ar/articles/physics-aligned-electronic-ground-state-learning-improves-generalization.