A Machine Learning Framework for Computing the Most Probable Paths of Stochastic Dynamical Systems

Abstract

The emergence of transition phenomena between metastable states induced by noise plays a fundamental role in a broad range of nonlinear systems. The computation of the most probable paths is a key issue to understand the mechanism of transition behaviors. Shooting method is a common technique for this purpose to solve the Euler-Lagrange equation for the associated action functional, while losing its efficacy in high-dimensional systems. In the present work, we develop a machine learning framework to compute the most probable paths in the sense of Onsager-Machlup action functional theory. Specifically, we reformulate the boundary value problem of Hamiltonian system and design a neural network to remedy the shortcomings of shooting method. The successful applications of our algorithms to several prototypical examples demonstrate its efficacy and accuracy for stochastic systems with both (Gaussian) Brownian noise and (non-Gaussian) Lévy noise. This novel approach is effective in exploring the internal mechanisms of rare events triggered by random fluctuations in various scientific fields.

22 pages, 13 figures

References in corpus (10)

• Data-driven discovery of coordinates and governing equations
• A Machine Learning Framework for Solving High-Dimensional Mean Field Game and Mean Field Control Problems
• Solving Fokker-Planck equation using deep learning
• Numerical computation of rare events via large deviation theory
• The Onsager-Machlup Function as Lagrangian for the Most Probable Path of a Jump-diffusion Process
• Relation of a New Interpretation of Stochastic Differential Equations to Ito Process
• Summing over trajectories of stochastic dynamics with multiplicative noise
• Most Probable Dynamics of Stochastic Dynamical Systems with Exponentially Light Jump Fluctuations
• Solving Inverse Stochastic Problems from Discrete Particle Observations Using the Fokker-Planck Equation and Physics-informed Neural Networks
• Two-scale large deviations for chemical reaction kinetics through second quantization path integral

Cited by in corpus (3)

• Controlling mean exit time of stochastic dynamical systems based on quasipotential and machine learning
• Estimating the Most Probable Transition Time for Stochastic Dynamical Systems
• Onsager-Machlup action functional for stochastic partial differential equations with Levy noise