Machine-Learned Leftmost Hessian Eigenvectors for Robust Transition State Finding

TL;DR

This paper introduces a machine-learning-based transition state optimizer that predicts the critical Hessian eigenvector, enabling robust and efficient TS finding comparable to full Hessian methods but at lower computational cost.

Contribution

The authors develop a novel ML-driven optimizer that predicts the leftmost Hessian eigenvector, improving robustness and efficiency in transition state searches without full Hessian calculations.

Findings

Recovers TS solutions as effectively as full Hessian methods

More robust from poor initial guesses

Reduces computational time compared to traditional approaches

Abstract

The reliable determination of transition states (TSs) benefits from second-order information for robust convergence and validation, but the computational expense of Hessians prohibits their routine use in TS optimization. Here, we present a machine-learning-driven TS optimizer that directly predicts the leftmost Hessian eigenvector (LMHE), the critical mode that locally approximates the reaction coordinate encompassing the TS. We demonstrate that our LMHE optimizer recovers TS solutions at the same rate as full Hessian optimizers, and more robustly from degraded initial guess geometries, thereby eliminating the excessively long wall times characteristic of full-Hessian approaches and reducing total gradient evaluations compared to standard quasi-Newton methods. We further improve accuracy and robustness using uncertainty quantification for identifying occasional LMHE prediction failures, that then falls back to a full Hessian update from the machine learned potential at that optimization step, avoiding expensive active learning. Overall our methodology and semi-automated workflow delivers second-order stability at first-order computational expense to provide a highly efficient engine for high-throughput reaction discovery.