Document Type
Article
Publication Date
August 2017
Publication Title
Physical Review X
Volume
7
Issue Number
3
DOI
10.1103/PhysRevX.7.031038
Keywords
Computational Physics, Condensed Matter Physics, Strongly Correlated Materials
Disciplines
Condensed Matter Physics | Physics
Abstract
Machine learning offers an unprecedented perspective for the problem of classifying phases in condensed matter physics. We employ neural network machine learning techniques to distinguish finite-temperature phases of the strongly-correlated fermions on cubic lattices. We show that a three-dimensional convolutional network trained on auxiliary field configurations produced by quantum Monte Carlo simulations of the Hubbard model can correctly predict the magnetic phase diagram of the model at the average density of one (half filling). We then use the network, trained at half filling, to explore the trend in the transition temperature as the system is doped away from half filling. This transfer learning approach predicts that the instability to the magnetic phase extends to at least 5% doping in this region. Our results pave the way for other machine learning applications in correlated quantum many-body systems.
Recommended Citation
Kelvin Ch'ng, Juan Carrasquilla, Roger Melko, and Ehsan Khatami. "Machine Learning Phases of Strongly Correlated Fermions" Physical Review X (2017). https://doi.org/10.1103/PhysRevX.7.031038
Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 License.
- Citations
- Citation Indexes: 302
- Usage
- Abstract Views: 40
- Downloads: 38
- Captures
- Readers: 316
- Mentions
- Blog Mentions: 1
Comments
This article was published in Physical Review X, volume 7, issue 3, July-September, 2017 and can be found online at this link: https://doi.org/10.1103/PhysRevX.7.031038
Published by the American Physical Society under the terms of the Creative Commons Attribution 4.0 International license. Further distribution of this work must maintain attribution to the author(s) and the published article’s title, journal citation, and DOI.