Many-body mobility edges in 1D and 2D revealed by convolutional neural networks
arXiv:2312.09223 · doi:10.1103/PhysRevB.109.075124
Abstract
We adapt a machine-learning approach to study the many-body localization transition in interacting fermionic systems on disordered 1D and 2D lattices. We perform supervised training of convolutional neural networks (CNNs) using labelled many-body wavefunctions at weak and strong disorder. In these limits, the average validation accuracy of the trained CNNs exceeds 99.95%. We use the disorder-averaged predictions of the CNNs to generate energy-resolved phase diagrams, which exhibit many-body mobility edges. We provide finite-size estimates of the critical disorder strengths at and for 1D and 2D systems of 16 sites respectively. Our results agree with the analysis of energy-level statistics and inverse participation ratio. By examining the convolutional layer, we unveil its feature extraction mechanism which highlights the pronounced peaks in localized many-body wavefunctions while rendering delocalized wavefunctions nearly featureless.
main text (7 pages with 4 figures) + bibliography (2 pages)
References in corpus (12)
- Thermalization and its mechanism for generic isolated quantum systems
- Many body localization and thermalization in quantum statistical mechanics
- Localization of interacting fermions at high temperature
- Many-body localization edge in the random-field Heisenberg chain
- The distribution of the ratio of consecutive level spacings in random matrix ensembles
- Learning phase transitions by confusion
- Discovering Phases, Phase Transitions and Crossovers through Unsupervised Machine Learning: A critical examination
- Restricted-Boltzmann-Machine Learning for Solving Strongly Correlated Quantum Systems
- Can we study the many-body localisation transition?
- Machine learning meets quantum physics
- Deep Learning the Quantum Phase Transitions in Random Two-Dimensional Electron Systems
- Learning What a Machine Learns in a Many-Body Localization Transition