Exploring the robust extrapolation of high-dimensional machine learning potentials

We show that, contrary to popular assumptions, predictions from machine learning potentials built upon highdimensional atom-density representations almost exclusively occur in regions of the representation space which lie outside the convex hull defined by the training set points. We then propose a perspective to rationalize the domain of robust extrapolation and accurate prediction of atomistic machine learning potentials in terms of the probability density induced by training points in the representation space.

Automated summary

This passage discusses the characteristics of machine learning potentials built upon high-dimensional atom-density representations, indicating that the probability density induced by training points in the representation space plays a significant role in robust extrapolation and accurate prediction.