Machine learning for many-body physics: efficient solution of dynamical mean-field theory
arXiv:1506.08858
Abstract
Machine learning methods for solving the equations of dynamical mean-field theory are developed. The method is demonstrated on the three dimensional Hubbard model. The key technical issues are defining a mapping of an input function to an output function, and distinguishing metallic from insulating solutions. Both metallic and Mott insulator solutions can be predicted. The validity of the machine learning scheme is assessed by comparing predictions of full correlation functions, of quasi-particle weight and particle density to values directly computed. The results indicate that with modest further development, machine learning approach may be an attractive computational efficient option for real materials predictions for strongly correlated systems.
main text 5 pages, supplemental 5 pages
Cited by in corpus (21)
- Quantum Entanglement in Neural Network States
- Machine Learning Topological States
- Machine Learning Topological Invariants with Neural Networks
- Bayesian optimization for tuning and selecting hybrid-density functionals
- Detection of phase transition via convolutional neural network
- Self-learning Monte Carlo with Deep Neural Networks
- Unifying Neural-network Quantum States and Correlator Product States via Tensor Networks
- Machine Learning Bell Nonlocality in Quantum Many-body Systems
- Extrapolating quantum observables with machine learning: Inferring multiple phase transitions from properties of a single phase
- Machine Learning meets Quantum Foundations: A Brief Survey
- Learning phase transitions from dynamics
- Matrix Product Operators for Sequence to Sequence Learning
- Thermodynamics and Feature Extraction by Machine Learning
- Machine learning for molecular dynamics with strongly correlated electrons
- Artificial Neural Network Based Computation for Out-of-Time-Ordered Correlators
- Neural Network flows of low q-state Potts and clock Models
- Visualizing Neural Network Developing Perturbation Theory
- Deep learning of topological phase transitions from entanglement aspects for two-dimensional chiral p-wave superconductors
- Ab initio machine learning in chemical compound space
- Induction and physical theory formation as well as universal computation by machine learning
- A computational high-throughput search for new ternary superalloys