Machine Learning Wavefunction

TL;DR

This paper discusses how machine learning models can effectively represent complex electronic wavefunctions in quantum chemistry, offering flexible and compact solutions that improve upon traditional methods through various examples and case studies.

Contribution

It introduces machine learning approaches for wavefunction representation, highlighting their advantages and limitations compared to traditional quantum chemistry methods.

Findings

Machine learning wavefunctions can capture complex electron interactions effectively.

ML-based methods offer more flexible and compact representations.

Case studies demonstrate practical advantages over traditional approaches.

Abstract

This chapter introduces the main ideas and the most important methods for representing the electronic wavefunction through machine learning models. The wavefunction of a N-electron system is an incredibly complicated mathematical object, and models thereof require enough flexibility to properly describe the complex interactions between the particles, but at the same time a sufficiently compact representation to be useful in practice. Machine learning techniques offer an ideal mathematical framework to satisfy these requirements, and provide algorithms for their optimization in both supervised and unsupervised fashions. In this chapter, various examples of machine learning wavefunctions are presented and their strengths and weaknesses with respect to traditional quantum chemical approaches are discussed; first in theory, and then in practice with two case studies.