# Machine learning the computational cost of quantum chemistry

## TL;DR

This paper develops quantum machine learning models to predict the computational cost of quantum chemistry tasks, significantly improving job scheduling efficiency and reducing CPU time overhead in molecular simulations.

## Contribution

It introduces QML models for predicting quantum chemistry computational costs, demonstrating their effectiveness across various systems and levels of theory.

## Key findings

- QML prediction errors decrease with larger training sets.
- QML models improve scheduling efficiency across multiple tasks.
- CPU time overhead reductions range from 10% to 90%.

## Abstract

Computational quantum mechanics based molecular and materials design campaigns consume increasingly more high-performance compute resources, making improved job scheduling efficiency desirable in order to reduce carbon footprint or wasteful spending. We introduce quantum machine learning (QML) models of the computational cost of common quantum chemistry tasks. For 2D non-linear toy systems, single point, geometry optimization, and transition state calculations the out of sample prediction error of QML models of wall times decays systematically with training set size. We present numerical evidence for a toy system containing two functions and three commonly used optimizer and for thousands of organic molecular systems including closed and open shell equilibrium structures, as well as transition states. Levels of electronic structure theory considered include B3LYP/def2-TZVP, MP2/6-311G(d), local CCSD(T)/VTZ-F12, CASSCF/VDZ-F12, and MRCISD+Q-F12/VDZ-F12. In comparison to conventional indiscriminate job treatment, QML based wall time predictions significantly improve job scheduling efficiency for all tasks after training on just thousands of molecules. Resulting reductions in CPU time overhead range from 10% to 90%.