Gaussian Process Regression for Transition State Search

TL;DR

This paper introduces a Gaussian process regression-based gradient algorithm for transition state search, significantly reducing energy and gradient evaluations compared to traditional methods.

Contribution

The paper presents a novel gradient-based transition state search algorithm using Gaussian process regression, including a method for initial point selection from reactant and product minima.

Findings

Reduces the number of energy evaluations needed

Outperforms dimer method in benchmarks

Effective on 27 test systems

Abstract

We implemented a gradient-based algorithm for transition state search which uses Gaussian process regression. Besides a description of the algorithm, we provide a method to find the starting point for the optimization if only the reactant and product minima are known. We perform benchmarks on 27 test systems against the dimer method and partitioned rational function optimization as implemented in the DL-FIND library. We found the new optimizer to significantly decrease the number of required energy and gradient evaluations.