Efficient ensemble uncertainty estimation in Gaussian Processes Regression

Abstract

Reliable uncertainty measures are required when using data based machine learning interatomic potentials (MLIPs) for atomistic simulations. In this work, we propose for sparse Gaussian Process Regression type MLIP a stochastic uncertainty measure akin to the query-by-committee approach often used in conjunction with neural network based MLIPs. The uncertainty measure is coined \textit{"label noise"} ensemble uncertainty as it emerges from adding noise to the energy labels in the training data. We find that this method of calculating an ensemble uncertainty is as well calibrated as the one obtained from the closed-form expression for the posterior variance when the sparse GPR is treated as a projected process. Comparing the two methods, our proposed ensemble uncertainty is, however, faster to evaluate than the closed-form expression. Finally, we demonstrate that the proposed uncertainty measure acts better to support a Bayesian search for optimal structure of Au${}_{20}$ clusters.

References in corpus (28)

• Gaussian Approximation Potentials: the accuracy of quantum mechanics, without the electrons
• Crystal Graph Convolutional Neural Networks for an Accurate and Interpretable Prediction of Material Properties
• On representing chemical environments
• Fast and Accurate Modeling of Molecular Atomization Energies with Machine Learning
• E(3)-Equivariant Graph Neural Networks for Data-Efficient and Accurate Interatomic Potentials
• Aleatoric and Epistemic Uncertainty in Machine Learning: An Introduction to Concepts and Methods
• PhysNet: A Neural Network for Predicting Energies, Forces, Dipole Moments and Partial Charges
• Machine-learning based interatomic potential for amorphous carbon
• Tensor field networks: Rotation- and translation-equivariant neural networks for 3D point clouds
• Machine Learning Molecular Dynamics for the Simulation of Infrared Spectra
• Alchemical and structural distribution based representation for improved QML
• Unified Representation of Molecules and Crystals for Machine Learning
• Committee neural network potentials control generalization errors and enable active learning
• Efficient global structure optimization with a machine learned surrogate model
• Active learning of reactive Bayesian force fields: Application to heterogeneous hydrogen-platinum catalysis dynamics
• Efficient Bayesian Inference of Atomistic Structure in Complex Functional Materials
• Cormorant: Covariant Molecular Neural Networks
• Accelerating CALYPSO Structure Prediction by Data-driven Learning of Potential Energy Surface
• Single-model uncertainty quantification in neural network potentials does not consistently outperform model ensembles
• Fast Uncertainty Estimates in Deep Learning Interatomic Potentials
• IrO2 Surface Complexions Identified Through Machine Learning and Surface Investigations
• Deep Ensembles vs. Committees for Uncertainty Estimation in Neural-Network Force Fields: Comparison and Application to Active Learning
• Uncertainty-biased molecular dynamics for learning uniformly accurate interatomic potentials
• Global optimization of atomic structures with gradient-enhanced Gaussian process regression
• Atomistic structure search using local surrogate mode
• A machine learning potential for simulating infrared spectra of nanosilicate clusters
• Coherent energy and force uncertainty in deep learning force fields
• Accelerating structure search using atomistic graph-based classifiers