Estimating Committor Functions via Deep Adaptive Sampling on Rare Transition Paths

2025-01-26

AI Summary

In molecular simulations, accurate estimation of the committor function—critical for characterizing rare transition events—is hindered by severe scarcity of transition-path data; conventional methods suffer from low sampling efficiency and poor generalizability. To address this, we propose the Deep Adaptive Sampling for Transition Paths (DASTR) framework, the first to model the non-negative committor loss integrand as an unnormalized density and approximate it using deep generative models (e.g., normalizing flows or diffusion models). DASTR integrates variational inference, physics-informed loss constraints, and adaptive importance sampling to enable targeted, efficient sampling of the transition-state region. Evaluated on both synthetic and real molecular systems, DASTR reduces committor estimation error significantly, decreases required sample size by an order of magnitude, and improves training stability and cross-system generalizability.

Technology Category

• Search and Optimization: Sampling/Simulation-based Search
• Intelligent Robots: State Estimation
• Machine Learning: Probabilistic Circuits and Graphical Models

Application Category

• User Modeling, Personalization and Recommendation: User modeling and simulation for interactive and conversational systems
• Web Mining and Content Analysis: Web data generation and simulation
• Graph Algorithms and Modeling for the Web: Graph embeddings and representation learning for Web-related graphs

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.

Problem

• Rare Event Simulation
• Neural Network Learning
• Transition Path Computation

Innovation

• DASTR
• rare event sampling
• neural network learning enhancement