Estimating Committor Functions via Deep Adaptive Sampling on Rare Transition Paths

TL;DR

This paper introduces DASTR, a deep adaptive sampling framework utilizing generative models to efficiently generate transition state data, significantly improving neural network approximation of committor functions in high-dimensional molecular simulations.

Contribution

The paper proposes a novel deep adaptive sampling method using generative models to efficiently generate transition data for accurate committor function estimation.

Findings

DASTR improves sampling efficiency in transition regions.

Neural network approximation of committor functions is significantly enhanced.

Method demonstrates effectiveness in simulations and real-world examples.

Abstract

The committor functions are central to investigating rare but important events in molecular simulations. It is known that computing the committor function suffers from the curse of dimensionality. Recently, using neural networks to estimate the committor function has gained attention due to its potential for high-dimensional problems. Training neural networks to approximate the committor function needs to sample transition data from straightforward simulations of rare events, which is very inefficient. The scarcity of transition data makes it challenging to approximate the committor function. To address this problem, we propose an efficient framework to generate data points in the transition state region that helps train neural networks to approximate the committor function. We design a Deep Adaptive Sampling method for TRansition paths (DASTR), where deep generative models are employed to generate samples to capture the information of transitions effectively. In particular, we treat a non-negative function in the integrand of the loss functional as an unnormalized probability density function and approximate it with the deep generative model. The new samples from the deep generative model are located in the transition state region and fewer samples are located in the other region. This distribution provides effective samples for approximating the committor function and significantly improves the accuracy. We demonstrate the effectiveness of the proposed method through both simulations and realistic examples.