A semigroup method for high dimensional committor functions based on neural network

Abstract

This paper proposes a new method based on neural networks for computing the high-dimensional committor functions that satisfy Fokker-Planck equations. Instead of working with partial differential equations, the new method works with an integral formulation based on the semigroup of the differential operator. The variational form of the new formulation is then solved by parameterizing the committor function as a neural network. There are two major benefits of this new approach. First, stochastic gradient descent type algorithms can be applied in the training of the committor function without the need of computing any mixed second-order derivatives. Moreover, unlike the previous methods that enforce the boundary conditions through penalty terms, the new method takes into account the boundary conditions automatically. Numerical results are provided to demonstrate the performance of the proposed method.

arXiv comment21 pages, 14 figures; Final version accepted at MSML 2021

References in corpus (5)

• Adam: A Method for Stochastic Optimization
• On Lazy Training in Differentiable Programming
• On Nonconvex Optimization for Machine Learning: Gradients, Stochasticity, and Saddle Points
• Approximate Temporal Difference Learning is a Gradient Descent for Reversible Policies
• Temporal-difference learning with nonlinear function approximation: lazy training and mean field regimes

Cited by in corpus (7)

• Computing committors via Mahalanobis diffusion maps with enhanced sampling data
• Inexact iterative numerical linear algebra for neural network-based spectral estimation and rare-event prediction
• Variational deep learning of equilibrium transition path ensembles
• Supervised Learning and the Finite-Temperature String Method for Computing Committor Functions and Reaction Rates
• Statistical Analysis of Tipping Pathways in Agent-Based Models
• On Committor Functions in Milestoning
• Committor functions via tensor networks