Scalable Bayesian Uncertainty Quantification for Neural Network Potentials: Promise and Pitfalls

12/15/2022
by   Stephan Thaler, et al.
0

Neural network (NN) potentials promise highly accurate molecular dynamics (MD) simulations within the computational complexity of classical MD force fields. However, when applied outside their training domain, NN potential predictions can be inaccurate, increasing the need for Uncertainty Quantification (UQ). Bayesian modeling provides the mathematical framework for UQ, but classical Bayesian methods based on Markov chain Monte Carlo (MCMC) are computationally intractable for NN potentials. By training graph NN potentials for coarse-grained systems of liquid water and alanine dipeptide, we demonstrate here that scalable Bayesian UQ via stochastic gradient MCMC (SG-MCMC) yields reliable uncertainty estimates for MD observables. We show that cold posteriors can reduce the required training data size and that for reliable UQ, multiple Markov chains are needed. Additionally, we find that SG-MCMC and the Deep Ensemble method achieve comparable results, despite shorter training and less hyperparameter tuning of the latter. We show that both methods can capture aleatoric and epistemic uncertainty reliably, but not systematic uncertainty, which needs to be minimized by adequate modeling to obtain accurate credible intervals for MD observables. Our results represent a step towards accurate UQ that is of vital importance for trustworthy NN potential-based MD simulations required for decision-making in practice.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
01/27/2021

Adversarial Attacks on Uncertainty Enable Active Learning for Neural Network Potentials

Neural network (NN)-based interatomic potentials provide fast prediction...
research
02/08/2022

Impact of Parameter Sparsity on Stochastic Gradient MCMC Methods for Bayesian Deep Learning

Bayesian methods hold significant promise for improving the uncertainty ...
research
08/11/2023

Target Detection on Hyperspectral Images Using MCMC and VI Trained Bayesian Neural Networks

Neural networks (NN) have become almost ubiquitous with image classifica...
research
05/02/2023

Single-model uncertainty quantification in neural network potentials does not consistently outperform model ensembles

Neural networks (NNs) often assign high confidence to their predictions,...
research
08/11/2023

Comparing the quality of neural network uncertainty estimates for classification problems

Traditional deep learning (DL) models are powerful classifiers, but many...
research
06/02/2021

Learning neural network potentials from experimental data via Differentiable Trajectory Reweighting

In molecular dynamics (MD), neural network (NN) potentials trained botto...
research
04/27/2023

Uncertainty Aware Neural Network from Similarity and Sensitivity

Researchers have proposed several approaches for neural network (NN) bas...

Please sign up or login with your details

Forgot password? Click here to reset