Optimizing adaptive sampling via Policy Ranking

TL;DR

This paper introduces a ranking-based framework for selecting optimal adaptive sampling policies in biomolecular simulations, significantly enhancing sampling efficiency and convergence speed.

Contribution

It proposes a systematic policy ranking approach for adaptive sampling, including algorithms for real-time policy evaluation, improving over traditional single-policy methods.

Findings

Policy ranking improves sampling efficiency

Multiple policies outperform single policy approaches

Faster convergence in biomolecular simulations

Abstract

Efficient sampling in biomolecular simulations is critical for accurately capturing the complex dynamical behaviors of biological systems. Adaptive sampling techniques aim to improve efficiency by focusing computational resources on the most relevant regions of phase space. In this work, we present a framework for identifying the optimal sampling policy through metric driven ranking. Our approach systematically evaluates the policy ensemble and ranks the policies based on their ability to explore the conformational space effectively. Through a series of biomolecular simulation case studies, we demonstrate that choice of a different adaptive sampling policy at each round significantly outperforms single policy sampling, leading to faster convergence and improved sampling performance. This approach takes an ensemble of adaptive sampling policies and identifies the optimal policy for the next round based on current data. Beyond presenting this ensemble view of adaptive sampling, we also propose two sampling algorithms that approximate this ranking framework on the fly. The modularity of this framework allows incorporation of any adaptive sampling policy making it versatile and suitable as a comprehensive adaptive sampling scheme.