AI and the World's Hard Problems · Chemistry & materials · arXiv · 2026-10-26
Contrastive Regularization of Machine Learning Potentials
Machine-learning interatomic potentials trained by minimizing mean squared error on DFT data can match held-out data yet drift into spurious minima when sampled, corrupting their thermodynamics. The authors introduce Contrastive Regularized MSE (CRMSE), a post-training step in which the potential acts as its own energy-based model and learns to reproduce the distribution it generates, without any new DFT data. On MD17 molecules, CRMSE restores physical sampling and recovers DFT free-energy profiles while keeping energy and force errors within chemical accuracy.