Solving eigenvalue PDEs of metastable diffusion processes using artificial neural networks

DOI10.1016/j.jcp.2022.111377OpenAlexW3210418243WikidataQ114163275 ScholiaQ114163275MaRDI QIDQ2157080

Wei Zhang, Christof Schütte, Tie-Jun Li

Publication date: 21 July 2022

Published in: Journal of Computational Physics (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2110.14523

zbMATH Keywords

variational characterizationmolecular dynamicsartificial neural networkeigenvalue PDEmetastable process

Mathematics Subject Classification ID

Stochastic analysis (60Hxx) Markov processes (60Jxx) Approximation methods and numerical treatment of dynamical systems (37Mxx)

Related Items (3)

Overcoming the timescale barrier in molecular dynamics: Transfer operators, variational principles and machine learning ⋮ Computing non-equilibrium trajectories by a deep learning approach ⋮ A deep learning method for computing eigenvalues of the fractional Schrödinger operator

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Variance reduction using nonreversible Langevin samplers
• On the numerical approximation of the Perron-Frobenius and Koopman operator
• A structure-preserving numerical discretization of reversible diffusions
• Data-driven model reduction and transfer operator approximation
• A data-driven approximation of the koopman operator: extending dynamic mode decomposition
• The Deep Ritz Method: a deep learning-based numerical algorithm for solving variational problems
• Exponential and uniform ergodicity of Markov processes
• Solving high-dimensional eigenvalue problems using deep neural networks: a diffusion Monte Carlo like approach
• Optimal approximation of piecewise smooth functions using deep ReLU neural networks
• Solving many-electron Schrödinger equation using deep neural networks
• Variational approach for learning Markov processes from time series data
• Ergodicity for SDEs and approximations: locally Lipschitz vector fields and degenerate noise.
• A mathematical formalization of the parallel replica dynamics
• Applied Koopmanism
• SLEPc
• Solving high-dimensional partial differential equations using deep learning
• Ergodic SDEs on submanifolds and related numerical sampling schemes
• Stochastic Processes and Applications
• Gradient Projection and Conditional Gradient Methods for Constrained Nonconvex Minimization
• Fluctuations in Markov Processes
• A Variational Approach to Modeling Slow Processes in Stochastic Dynamical Systems
• Perturbation bounds for means of eigenvalues and invariant subspaces
• Partial differential equations and stochastic methods in molecular dynamics
• Metastability
• Inequalities: theory of majorization and its applications

This page was built for publication: Solving eigenvalue PDEs of metastable diffusion processes using artificial neural networks