Model-free quantification of completeness, uncertainties, and outliers in atomistic machine learning using information theory

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Schwalbe-Koda, Daniel, Hamel, Sebastien, Sadigh, Babak, Zhou, Fei, Lordi, Vincenzo
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866908344483053568
author Schwalbe-Koda, Daniel
Hamel, Sebastien
Sadigh, Babak
Zhou, Fei
Lordi, Vincenzo
author_facet Schwalbe-Koda, Daniel
Hamel, Sebastien
Sadigh, Babak
Zhou, Fei
Lordi, Vincenzo
contents An accurate description of information is relevant for a range of problems in atomistic machine learning (ML), such as crafting training sets, performing uncertainty quantification (UQ), or extracting physical insights from large datasets. However, atomistic ML often relies on unsupervised learning or model predictions to analyze information contents from simulation or training data. Here, we introduce a theoretical framework that provides a rigorous, model-free tool to quantify information contents in atomistic simulations. We demonstrate that the information entropy of a distribution of atom-centered environments explains known heuristics in ML potential developments, from training set sizes to dataset optimality. Using this tool, we propose a model-free UQ method that reliably predicts epistemic uncertainty and detects out-of-distribution samples, including rare events in systems such as nucleation. This method provides a general tool for data-driven atomistic modeling and combines efforts in ML, simulations, and physical explainability.
format Preprint
id arxiv_https___arxiv_org_abs_2404_12367
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Model-free quantification of completeness, uncertainties, and outliers in atomistic machine learning using information theory
Schwalbe-Koda, Daniel
Hamel, Sebastien
Sadigh, Babak
Zhou, Fei
Lordi, Vincenzo
Materials Science
Machine Learning
Chemical Physics
An accurate description of information is relevant for a range of problems in atomistic machine learning (ML), such as crafting training sets, performing uncertainty quantification (UQ), or extracting physical insights from large datasets. However, atomistic ML often relies on unsupervised learning or model predictions to analyze information contents from simulation or training data. Here, we introduce a theoretical framework that provides a rigorous, model-free tool to quantify information contents in atomistic simulations. We demonstrate that the information entropy of a distribution of atom-centered environments explains known heuristics in ML potential developments, from training set sizes to dataset optimality. Using this tool, we propose a model-free UQ method that reliably predicts epistemic uncertainty and detects out-of-distribution samples, including rare events in systems such as nucleation. This method provides a general tool for data-driven atomistic modeling and combines efforts in ML, simulations, and physical explainability.
title Model-free quantification of completeness, uncertainties, and outliers in atomistic machine learning using information theory
topic Materials Science
Machine Learning
Chemical Physics
url https://arxiv.org/abs/2404.12367