Comment on "Fast and Accurate Modeling of Molecular Atomization Energies with Machine Learning"

TL;DR

This paper provides a critical commentary on the methods and conclusions of Rupp et al.'s 2012 study on machine learning models for molecular atomization energies, highlighting potential limitations and offering insights for future research.

Contribution

It offers a detailed critique and analysis of the original work, emphasizing areas for improvement and clarification in modeling molecular energies with machine learning.

Findings

Identifies limitations in the original modeling approach

Suggests alternative methods for improved accuracy

Highlights the importance of data quality and representation

Abstract

A Comment on the Letter by M. Rupp et al., Phys. Rev. Lett. 108 058301 (2012).