Learning phase transitions from dynamics

Abstract

We propose the use of recurrent neural networks for classifying phases of matter based on the dynamics of experimentally accessible observables. We demonstrate this approach by training recurrent networks on the magnetization traces of two distinct models of one-dimensional disordered and interacting spin chains. The obtained phase diagram for a well-studied model of the many-body localization transition shows excellent agreement with previously known results obtained from time-independent entanglement spectra. For a periodically-driven model featuring an inherently dynamical time-crystalline phase, the phase diagram that our network traces in a previously-unexplored regime coincides with an order parameter for its expected phases.

5 pages + 3 fig, appendix + 5 fig

References in corpus (19)

• Many body localization and thermalization in quantum statistical mechanics
• Localization of interacting fermions at high temperature
• On Calibration of Modern Neural Networks
• Many-body localization edge in the random-field Heisenberg chain
• Learning phase transitions by confusion
• Many-body localization in periodically driven systems
• Many-Body Localization in a Quasiperiodic System
• Recent progress in many-body localization
• Restricted-Boltzmann-Machine Learning for Solving Strongly Correlated Quantum Systems
• Machine learning vortices at the Kosterlitz-Thouless transition
• Unsupervised machine learning account of magnetic transitions in the Hubbard model
• Machine Learning of Explicit Order Parameters: From the Ising Model to SU(2) Lattice Gauge Theory
• Chiral Floquet Phases of Many-body Localized Bosons
• Machine learning out-of-equilibrium phases of matter
• Machine learning for many-body physics: The case of the Anderson impurity model
• Deep Learning the Quantum Phase Transitions in Random Two-Dimensional Electron Systems
• Quantum phase recognition via unsupervised machine learning
• Machine learning for many-body physics: efficient solution of dynamical mean-field theory
• Machine learning for predictive estimation of qubit dynamics subject to dephasing

Cited by in corpus (40)

• Machine learning and the physical sciences
• Big-Data Science in Porous Materials: Materials Genomics and Machine Learning
• Discovering physical concepts with neural networks
• From Bloch Oscillations to Many Body Localization in Clean Interacting Systems
• Many-body localization and delocalization in large quantum chains
• Machine Learning for Quantum Matter
• Extrapolating quantum observables with machine learning: Inferring multiple phase transitions from properties of a single phase
• Symbolic Pregression: Discovering Physical Laws from Distorted Video
• Thermodynamics and Feature Extraction by Machine Learning
• Drawing Phase Diagrams of Random Quantum Systems by Deep Learning the Wave Functions
• Divergence of predictive model output as indication of phase transitions
• Unsupervised learning of topological phase transitions using Calinski-Harabaz index
• Mapping distinct phase transitions to a neural network
• Interpretable machine learning for inferring the phase boundaries in a nonequilibrium system
• Neural network setups for a precise detection of the many-body localization transition: finite-size scaling and limitations
• Machine Learning of Implicit Combinatorial Rules in Mechanical Metamaterials
• Phase diagram study of a two-dimensional frustrated antiferromagnet via unsupervised machine learning
• Extending machine learning classification capabilities with histogram reweighting
• Homogeneous Floquet time crystal from weak ergodicity breaking
• Detecting ergodic bubbles at the crossover to many-body localization using neural networks
• Designing quantum many-body matter with conditional generative adversarial networks
• Approximation of quantum control correction scheme using deep neural networks
• Distinguishing an Anderson Insulator from a Many-Body Localized phase through space-time snapshots with Neural Networks
• Neural Network flows of low q-state Potts and clock Models
• Replacing neural networks by optimal analytical predictors for the detection of phase transitions
• Multi-faceted machine learning of competing orders in disordered interacting systems
• Learning Order Parameters from Videos of Dynamical Phases for Skyrmions with Neural Networks
• Forecasting high-impact research topics via machine learning on evolving knowledge graphs
• Unsupervised Learning of Rydberg Atom Array Phase Diagram with Siamese Neural Networks
• A learning algorithm with emergent scaling behavior for classifying phase transitions
• Transfer learning from Hermitian to non-Hermitian quantum many-body physics
• Learning What a Machine Learns in a Many-Body Localization Transition
• Machine Learning S-Wave Scattering Phase Shifts Bypassing the Radial Schrödinger Equation
• Berezinskii-Kosterlitz-Thouless transition from Neural Network Flows
• Renormalization-group-inspired neural networks for computing topological invariants
• Learning phase transitions by siamese neural network
• Unsupervised Learning of Symmetry Protected Topological Phase Transitions
• Entanglement Clustering for ground-stateable quantum many-body states
• Global exploration of phase behavior in frustrated Ising models using unsupervised learning techniques
• Learning from imperfections: constructing phase diagrams from atomic imaging of fluctuations