Can machines learn density functionals? Past, present, and future of ML in DFT
Computational Physics
2025-03-04 v1 Materials Science
Chemical Physics
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.
Keywords
Cite
@article{arxiv.2503.01709,
title = {Can machines learn density functionals? Past, present, and future of ML in DFT},
author = {Ryosuke Akashi and Mihira Sogal and Kieron Burke},
journal= {arXiv preprint arXiv:2503.01709},
year = {2025}
}
Comments
46 pages, 5 figures, 2 tables. Submitted to "Machine Learning in Condensed Matter Physics - Significance, Challenges, and Future Directions" (Springer Series in Solid-State Sciences)