Deep Learning Method for Computing Committor Functions with Adaptive Sampling
This work addresses the problem of quantifying transitions between metastable states in dynamical systems for researchers in computational physics or chemistry, representing an incremental improvement with novel sampling schemes.
The authors tackled the challenge of sampling adequate data for computing high-dimensional committor functions in complex systems at low temperatures by proposing a deep learning method with two novel adaptive sampling schemes, resulting in demonstrated efficiency in high-dimensional systems like alanine dipeptide and a solvated dimer system.
The committor function is a central object for quantifying the transitions between metastable states of dynamical systems. Recently, a number of computational methods based on deep neural networks have been developed for computing the high-dimensional committor function. The success of the methods relies on sampling adequate data for the transition, which still is a challenging task for complex systems at low temperatures. In this work, we propose a deep learning method with two novel adaptive sampling schemes (I and II). In the two schemes, the data are generated actively with a modified potential where the bias potential is constructed from the learned committor function. We theoretically demonstrate the advantages of the sampling schemes and show that the data in sampling scheme II are uniformly distributed along the transition tube. This makes a promising method for studying the transition of complex systems. The efficiency of the method is illustrated in high-dimensional systems including the alanine dipeptide and a solvated dimer system.