SOURCE-LINKED INTELLIGENCE

AdaptNTK: Adaptive Uncertainty Quantification and Active Learning for Neural Network Potentials

arXiv · AI, language, vision and robotics · article · Aug 31, 2026 · UTC

Machine learning interatomic potentials bridge the gap between quantum chemical precision and classical computational speed, enabling molecular dynamics simulations with first-principles accuracy. Their reliability is often improved through active learning, which iteratively expands the training set by identifying uncertain, out-of-distribution configurations. Existing uncertainty-quantification methods often involve a trade-off between computational cost and reliability, and generally cannot account for redundancy as an acquisition batch is assembled. Here, we introduce AdaptNTK, a single-mod

Read original source ↗ Open in workspace

recordType

paper

region

Global