Neural networks-based variationally enhanced sampling

DOI10.1073/PNAS.1907975116MaRDI QIDQ5218536zbMATH OpenOpenAlexWikidataFDO

Authors Luigi Bonati, Yueyu Zhang, Michele Parrinello

Publication date 4 March 2020

Published in Proceedings of the National Academy of Sciences (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/1904.01305

Mathematics Subject Classification ID

Neural nets applied to problems in time-dependent statistical mechanics (82C32)

Abstract: Sampling complex free energy surfaces is one of the main challenges of modern atomistic simulation methods. The presence of kinetic bottlenecks in such surfaces often renders a direct approach useless. A popular strategy is to identify a small number of key collective variables and to introduce a bias potential that is able to favor their fluctuations in order to accelerate sampling. Here we propose to use machine learning techniques in conjunction with the recent variationally enhanced sampling method [Valsson and Parrinello, Physical Review Letters 2014] to determine such potential. This is achieved by expressing the bias as a neural network. The parameters are determined in a reinforcement learning scheme aimed at minimizing the variationally enhanced sampling functional. This required the development of a new and more efficient minimization technique. The expressivity of neural networks allows accelerating sampling in systems with rapidly varying free energy surfaces, removing boundary effects artifacts, and making one more step towards being able to handle several collective variables.

Recommendations

• Deep Potential: A General Representation of a Many-Body Potential Energy Surface
• Free energy computations by minimization of Kullback-Leibler divergence: An efficient adaptive biasing potential method for sparse representations
• Enhanced sampling of multidimensional free-energy landscapes using adaptive biasing forces
• Molecular modeling by machine learning
• Adaptive force biasing algorithms: new convergence results and tensor approximations of the bias

Cited in

(6)

• Quasi-Random Sampling for Multivariate Distributions via Generative Neural Networks
• An Acceleration Strategy for Randomize-Then-Optimize Sampling Via Deep Neural Networks
• A mathematical framework for learning probability distributions
• An energy-based model approach to rare event probability estimation
• Consensus-based adaptive sampling and approximation for high-dimensional energy landscapes
• Local antithetic sampling with scrambled nets

This page was built for publication: Neural networks-based variationally enhanced sampling

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5218536)