HOAX: A Hyperparameter Optimization Algorithm Explorer for Neural Networks

TL;DR

This paper introduces HOAX, an automated framework for hyperparameter optimization of neural networks used to generate potential energy surfaces, significantly reducing computational costs in quantum chemistry.

Contribution

HOAX provides a user-friendly, automated approach to hyperparameter tuning for neural networks in quantum chemistry, improving efficiency and accuracy of PES modeling.

Findings

HOAX effectively automates hyperparameter optimization for neural networks.

Neural network PESs show good agreement with ab initio PESs.

The framework compares multiple optimization algorithms for best results.

Abstract

Computational chemistry has become an important tool to predict and understand molecular properties and reactions. Even though recent years have seen a significant growth in new algorithms and computational methods that speed up quantum chemical calculations, the bottleneck for trajectory-based methods to study photoinduced processes is still the huge number of electronic structure calculations. In this work, we present an innovative solution, in which the amount of electronic structure calculations is drastically reduced, by employing machine learning algorithms and methods borrowed from the realm of artificial intelligence. However, applying these algorithms effectively requires finding optimal hyperparameters, which remains a challenge itself. Here we present an automated user-friendly framework, HOAX, to perform the hyperparameter optimization for neural networks, which bypasses the need for a lengthy manual process. The neural network generated potential energy surfaces (PESs) reduces the computational costs compared to the ab initio-based PESs. We perform a comparative investigation on the performance of different hyperparameter optimiziation algorithms, namely grid search, simulated annealing, genetic algorithm, and bayesian optimizer in finding the optimal hyperparameters necessary for constructing the well-performing neural network in order to fit the PESs of small organic molecules. Our results show that this automated toolkit not only facilitate a straightforward way to perform the hyperparameter optimization but also the resulting neural networks-based generated PESs are in reasonable agreement with the ab initio-based PESs.