Machine Learning Phases of Strongly Correlated Fermions
Aug 30, 2017Citations per year
Abstract: (APS)
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.1 MoreReceived 14 June 2017DOI:https://doi.org/10.1103/PhysRevX.7.031038Published 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.Published by the American Physical SocietyPhysics Subject Headings (PhySH)Research AreasAntiferromagnetismMagnetic phase transitionsPhase diagramsTransition temperatureTechniquesHubbard modelLattice models in condensed matterMachine learningQuantum Monte CarloCondensed Matter, Materials & Applied Physics- Condensed Matter, Materials & Applied Physics
- Antiferromagnetism
- Magnetic phase transitions
- Phase diagrams
- Transition temperature
- Hubbard model
- Lattice models in condensed matter
- Machine learning
- Quantum Monte Carlo
References(33)
Figures(0)