Training collective variables for enhanced sampling via neural networks based discriminant analysis

TL;DR

This paper reviews a neural network-based discriminant analysis method for designing collective variables that improve sampling efficiency in molecular dynamics by capturing key physical changes.

Contribution

It introduces a data-driven approach combining Fisher's discriminant analysis with neural networks to create effective collective variables for enhanced sampling.

Findings

Effective in accelerating sampling of rare events

Identifies key physical descriptors during transitions

Compresses metastable fluctuations into low-dimensional space

Abstract

A popular way to accelerate the sampling of rare events in molecular dynamics simulations is to introduce a potential that increases the fluctuations of selected collective variables. For this strategy to be successful, it is critical to choose appropriate variables. Here we review some recent developments in the data-driven design of collective variables, with a focus on the combination of Fisher's discriminant analysis and neural networks. This approach allows to compress the fluctuations of metastable states into a low-dimensional representation. We illustrate through several examples the effectiveness of this method in accelerating the sampling, while also identifying the physical descriptors that undergo the most significant changes in the process.