Can machines learn density functionals? Past, present, and future of ML in DFT

2025/03/03 by Ryosuke Akashi, Mihira Sogal, Akashi, Ryosuke +3 · 1 voice · 3 citations
Materials Science · Physics and Astronomy · #Density functional theory #Key (lock) #Machine Learning in Materials Science #Time-dependent density functional theory #cond-mat.mtrl-sci #physics.chem-ph #physics.comp-ph

paper · pdf · doi:10.48550/arxiv.2503.01709

published in arXiv (Cornell University) (Cornell University)

openalex publication_date 2025/03/03 · openalex created_date 2025/10/12 · openalex updated_date 2026/08/05

Abstract

Density functional theory has become the world's favorite electronic structure method, and is routinely applied to both materials and molecules. Here, we review recent attempts to use modern machine-learning to improve density functional approximations. Many different researchers have tried many different approaches, but some common themes and lessons have emerged. We discuss these trends and where they might bring us in the future.

Citations

• Thirty years of density functional theory in computational chemistry: an overview and extensive assessment of 200 density functionals
• Playing Atari with Deep Reinforcement Learning
• ImageNet classification with deep convolutional neural networks
• Ab Initio Calculation of Vibrational Absorption and Circular Dichroism Spectra Using Density Functional Force Fields

Cited by

• Quantum statistical mechanics: Gauge invariance, operator shifting, hyperdensity functionals, and nonequilibrium sum rules
• Accurate and scalable exchange-correlation with deep learning
• Machine learning potentials for modeling alloys across compositions

Discussions

• Can machines learn density functionals? Past, present, and future of ML in DFT arxiv.org/abs/2503.01709 #compchem [bsky, 17 points, 0 comments]

Related

• Using Machine Learning to Find New Density Functionals
• Machine learning for accuracy in density functional approximations
• Completing density functional theory by machine-learning hidden messages from molecules
• Machine Learning approaches to classical density functional theory
• Density functionals from deep learning