Information theory unifies atomistic machine learning, uncertainty quantification, and materials thermodynamics

arXiv:2404.12367v1 Announce Type: cross
Abstract: An accurate description of information is relevant for a range of problems in atomistic modeling, such as sampling methods, detecting rare events, analyzing datasets, or performing uncertainty quantification (UQ) in machine learning (ML)-driven simulations. Although individual methods have been proposed for each of these tasks, they lack a common theoretical background integrating their solutions. Here, we introduce an information theoretical framework that unifies predictions of phase transformations, kinetic events, dataset optimality, and model-free UQ from …

abstract arxiv cond-mat.mtrl-sci cs.lg datasets events information machine machine learning materials modeling physics.chem-ph quantification sampling simulations theory type uncertainty