Solving for high dimensional committor functions using artificial neural networks
This work addresses a computational challenge in transition path theory for researchers in stochastic processes, but it appears incremental as it applies an existing neural network approach to a known bottleneck.
The authors tackled the problem of approximating high-dimensional committor functions, which describe transitions in stochastic processes, by proposing a neural network method that optimizes weights via stochastic algorithms, achieving moderate accuracy in numerical examples.
In this note we propose a method based on artificial neural network to study the transition between states governed by stochastic processes. In particular, we aim for numerical schemes for the committor function, the central object of transition path theory, which satisfies a high-dimensional Fokker-Planck equation. By working with the variational formulation of such partial differential equation and parameterizing the committor function in terms of a neural network, approximations can be obtained via optimizing the neural network weights using stochastic algorithms. The numerical examples show that moderate accuracy can be achieved for high-dimensional problems.