Committor functions via tensor networks

Abstract

We propose a novel approach for computing committor functions, which describe transitions of a stochastic process between metastable states. The committor function satisfies a backward Kolmogorov equation, and in typical high-dimensional settings of interest, it is intractable to compute and store the solution with traditional numerical methods. By parametrizing the committor function in a matrix product state/tensor train format and using a similar representation for the equilibrium probability density, we solve the variational formulation of the backward Kolmogorov equation with linear time and memory complexity in the number of dimensions. This approach bypasses the need for sampling the equilibrium distribution, which can be difficult when the distribution has multiple modes. Numerical results demonstrate the effectiveness of the proposed method for high-dimensional problems.

References in corpus (7)

• DGM: A deep learning algorithm for solving partial differential equations
• Matrix Product States, Projected Entangled Pair States, and variational renormalization group methods for quantum spin systems
• Solving high-dimensional partial differential equations using deep learning
• Advances on Tensor Network Theory: Symmetries, Fermions, Entanglement, and Holography
• Galerkin Approximation of Dynamical Quantities using Trajectory Data
• Active Importance Sampling for Variational Objectives Dominated by Rare Events: Consequences for Optimization and Generalization
• A semigroup method for high dimensional committor functions based on neural network