Interpretable Machine Learning Study of Many-Body Localization Transition in Disordered Quantum Ising Spin Chains

Abstract

We apply support vector machine (SVM) to study the phase transition between many-body localized and thermal phases in a disordered quantum Ising chain in a transverse external field. The many-body eigenstate energy $E$ is bounded by a bandwidth $W=E_{max}-E_{min}$. The transition takes place on a phase diagram spanned by the energy density $\epsilon =2(E-E_{min})/W$ and the disorder strength $\delta J$ of the spin interaction uniformly distributed within $[-\delta J,\delta J]$, formally parallel to the mobility edge in Anderson localization. In our study we use the labeled probability density of eigenstate wavefunctions belonging to the deeply localized and thermal regimes at two different energy densities ($\epsilon$'s) as the training set, i.e., providing labeled data at four corners of the phase diagram. Then we employ the trained SVM to predict the whole phase diagram. The obtained phase boundary qualitatively agrees with previous work using entanglement entropy to characterize these two phases. We further analyze the decision function of the SVM to interpret its physical meaning and find that it is analogous to the inverse participation ratio in configuration space. Our findings demonstrate the ability of the SVM to capture potential quantities that may characterize the many-body localization phase transition.

arXiv commentrevised version, 11 pages, 12 figures

References in corpus (39)

• Chaos and Quantum Thermalization
• Thermalization and its mechanism for generic isolated quantum systems
• Area laws for the entanglement entropy - a review
• Many body localization and thermalization in quantum statistical mechanics
• Solving the Quantum Many-Body Problem with Artificial Neural Networks
• Anderson Transitions
• Metal-insulator transition in a weakly interacting many-electron system with localized single-particle states
• Machine learning phases of matter
• Many-body localization edge in the random-field Heisenberg chain
• Unbounded growth of entanglement in models of many-body localization
• Many body localization in Heisenberg XXZ magnet in a random field
• Local conservation laws and the structure of the many-body localized states
• Learning phase transitions by confusion
• Discovering Phase Transitions with Unsupervised Learning
• Universal slow growth of entanglement in interacting strongly disordered systems
• Many-body localization in a disordered quantum Ising chain
• Integrals of motion in the Many-Body localized phase
• Area laws in a many-body localized state and its implications for topological order
• Spectral signatures of many-body localization with interacting photons
• Localization protected quantum order
• Many-body localization in one dimension as a dynamical renormalization group fixed point
• Many-body localization characterized from a one-particle perspective
• Spectral features of a many-body localized system weakly coupled to a heat bath
• Probing many-body localization with neural networks
• Many body localization and thermalization: insights from the entanglement spectrum
• Kernel methods for interpretable machine learning of order parameters
• Universal behavior beyond multifractality in quantum many-body systems
• Many body localization in the presence of a single particle mobility edge
• Machine Learning ${\mathbb{Z}}_2$ Quantum Spin Liquids with Quasi-particle Statistics
• Long tail distributions near the many body localization transition
• Extended nonergodic states in disordered many-body quantum systems
• Global characteristics of all eigenstates of local many-body Hamiltonians: participation ratio and entanglement entropy
• Machine Learning Many-Body Localization: Search for the Elusive Nonergodic Metal
• Anderson model on Bethe lattices: density of states, localization properties and isolated eigenvalue
• Many-body mobility edge due to symmetry-constrained dynamics and strong interactions
• Many-body mobility edges in a one-dimensional model of interacting fermions
• Many-body localization and mobility edge in a disordered Heisenberg spin ladder
• Universality of the metal-insulator transition in three-dimensional disordered systems
• The Renyi Entropy and the Multifractal Spectrum of Systems Near the Localization Transition

Cited by in corpus (25)

• Machine learning and the physical sciences
• Many-body localization and delocalization in large quantum chains
• Machine Learning for Quantum Matter
• Drawing Phase Diagrams of Random Quantum Systems by Deep Learning the Wave Functions
• Transition to a many-body localized regime in a two-dimensional disordered quantum dimer model
• Interpreting machine learning of topological quantum phase transitions
• Mapping distinct phase transitions to a neural network
• Neural network setups for a precise detection of the many-body localization transition: finite-size scaling and limitations
• Exploring neural network training strategies to determine phase transitions in frustrated magnetic models
• Analyzing non-equilibrium quantum states through snapshots with artificial neural networks
• Extending machine learning classification capabilities with histogram reweighting
• Entanglement-guided architectures of machine learning by quantum tensor network
• Hessian-based toolbox for reliable and interpretable machine learning in physics
• Distinguishing an Anderson Insulator from a Many-Body Localized phase through space-time snapshots with Neural Networks
• Replacing neural networks by optimal analytical predictors for the detection of phase transitions
• Learning phase transitions from regression uncertainty: A new regression-based machine learning approach for automated detection of phases of matter
• A learning algorithm with emergent scaling behavior for classifying phase transitions
• Emergence of a finite-size-scaling function in the supervised learning of the Ising phase transition
• Transfer learning from Hermitian to non-Hermitian quantum many-body physics
• Rise and Fall of Anderson Localization by Lattice Vibrations: A Time-Dependent Machine Learning Approach
• Effective classical correspondence of the Mott transition
• Fluctuation based interpretable analysis scheme for quantum many-body snapshots
• Many-body mobility edges in 1D and 2D revealed by convolutional neural networks
• On the criticality of the configuration-space statistical geometry
• Autonomous Discovery of the Ising Model's Critical Parameters with Reinforcement Learning