A deep learning method for computing committor functions with adaptive sampling

DOI10.1137/24M1654750MaRDI QIDQ6917925zbMATH OpenFDO

Authors Bo Lin, Weiqing Ren

Publication date 10 October 2025

Published in SIAM Journal on Scientific Computing (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1137/24M1654750

zbMATH Keywords

adaptive samplingcommittor functiondeep learningrare event

Mathematics Subject Classification ID

PDEs in connection with biology, chemistry and other natural sciences (35Q92) PDEs with randomness, stochastic partial differential equations (35R60) Applications of statistics in engineering and industry; control charts (62P30) Monte Carlo methods (65C05) Finite element, Rayleigh-Ritz and Galerkin methods for boundary value problems involving PDEs (65N30) Mesh generation, refinement, and adaptive methods for boundary value problems involving PDEs (65N50) Artificial neural networks and deep learning (68T07) Biochemistry, molecular biology (92C40) Protein sequences, DNA sequences (92D20)

Cites work

• Committor functions via tensor networks
• Computing committors in collective variables via Mahalanobis diffusion maps
• Handbook of stochastic methods for physics, chemistry and natural sciences.
• Local and global perspectives on diffusion maps in the analysis of molecular systems
• New development in freefem++
• Point cloud discretization of Fokker-Planck operators for committor functions
• Solving for high-dimensional committor functions using artificial neural networks
• Towards a theory of transition paths

Cited in

(1)

• Score-based physics-informed learning framework for stochastic dynamics

This page was built for publication: A deep learning method for computing committor functions with adaptive sampling

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6917925)