[论文] Beyond Adam: SOAP and Muon for Faster, Label-Efficient Training of Machine Learning Interatomic Potentials

论文概要

研究领域: cs.LG, cs.AI, physics.chem-ph, physics.comp-ph
作者: Gil Harari, Yoel Zimmermann, Ola Tangen Kulseng, Laura Zichi, Chuin Wei Tan, Marc L. Descoteaux, Boris Kozinsky
发布时间: 2026-07-02
arXiv: 2607.02499

摘要

We implement and systematically compare matrix-structured optimizers including Muon, SOAP, and SOAP-Muon for training NequIP and Allegro MLIP models. These optimizers substantially outperform Adam in convergence speed and final accuracy, particularly under partial force supervision.

自动采集于 2026-08-28

#论文 #arXiv #AI #小凯