Classifying Snapshots of the Doped Hubbard Model with Machine Learning

Abstract

Quantum gas microscopes for ultracold atoms can provide high-resolution real-space snapshots of complex many-body systems. We implement machine learning to analyze and classify such snapshots of ultracold atoms. Specifically, we compare the data from an experimental realization of the two-dimensional Fermi-Hubbard model to two theoretical approaches: a doped quantum spin liquid state of resonating valence bond type, and the geometric string theory, describing a state with hidden spin order. This approach considers all available information without a potential bias towards one particular theory by the choice of an observable and can therefore select the theory which is more predictive in general. Up to intermediate doping values, our algorithm tends to classify experimental snapshots as geometric-string-like, as compared to the doped spin liquid. Our results demonstrate the potential for machine learning in processing the wealth of data obtained through quantum gas microscopy for new physical insights.

arXiv comment4 pages, 3 figures + 4 pages, 5 figures

References in corpus (27)

• Solving the Quantum Many-Body Problem with Artificial Neural Networks
• Machine learning phases of matter
• Many-body quantum state tomography with neural networks
• Experimental realization of a long-range antiferromagnet in the Hubbard model with ultracold atoms
• Learning phase transitions by confusion
• Observation of antiferromagnetic correlations in the Hubbard model with ultracold atoms
• Short-range quantum magnetism of ultracold fermions in an optical lattice
• Machine learning quantum phases of matter beyond the fermion sign problem
• Observation of Spatial Charge and Spin Correlations in the 2D Fermi-Hubbard Model
• Bad metallic transport in a cold atom Fermi-Hubbard system
• Symmetries and many-body excited states with neural-network quantum states
• Identifying Quantum Phase Transitions using Artificial Neural Networks on Experimental Data
• Revealing Hidden Antiferromagnetic Correlations in Doped Hubbard Chains via String Correlators
• Mutual Information, Neural Networks and the Renormalization Group
• Machine learning vortices at the Kosterlitz-Thouless transition
• Machine Learning in Electronic Quantum Matter Imaging Experiments
• Spin Transport in a Mott Insulator of Ultracold Fermions
• Machine learning of quantum phase transitions
• A quantum dimer model for the pseudogap metal
• Direct observation of incommensurate magnetism in Hubbard chains
• String excitations of a hole in a quantum antiferromagnet and photoelectron spectrospopy
• Probing hidden spin order with interpretable machine learning
• Evidence for composite nature of quasiparticles in the 2D t-J model
• Efficient Representation of Topologically Ordered States with Restricted Boltzmann Machines
• Learning multiple order parameters with interpretable machines
• Microscopic spinon-chargon theory of magnetic polarons in the t-J model
• Meson formation in mixed-dimensional t-J models

Cited by in corpus (90)

• Study of the Two-Dimensional Frustrated J1-J2 Model with Neural Network Quantum States
• Provably efficient machine learning for quantum many-body problems
• String patterns in the doped Hubbard model
• Machine Learning for Quantum Matter
• Integrating Neural Networks with a Quantum Simulator for State Reconstruction
• Quantum Adversarial Machine Learning
• Exploration of doped quantum magnets with ultracold atoms
• Unsupervised machine learning of topological phase transitions from experimental data
• Realizing Altermagnetism in Fermi-Hubbard Models with Ultracold Atoms
• Precise measurement of quantum observables with neural-network estimators
• Parton theory of ARPES spectra in anti-ferromagnetic Mott insulators
• Correlator Convolutional Neural Networks: An Interpretable Architecture for Image-like Quantum Matter Data
• Are there universal signatures of topological phases in high harmonic generation? Probably not
• Harnessing Interpretable and Unsupervised Machine Learning to Address Big Data from Modern X-ray Diffraction
• Unsupervised learning universal critical behavior via the intrinsic dimension
• Machine learning discovery of new phases in programmable quantum simulator snapshots
• Interpreting machine learning of topological quantum phase transitions
• One-Component Order Parameter in URu${}_2$Si${}_2$ Uncovered by Resonant Ultrasound Spectroscopy and Machine Learning
• Unsupervised learning of topological phase transitions using Calinski-Harabaz index
• Visualizing Strange Metallic Correlations in the 2D Fermi-Hubbard Model with AI
• Efficient MPS methods for extracting spectral information on rings and cylinders
• Machine Learning of Implicit Combinatorial Rules in Mechanical Metamaterials
• Model-Independent Learning of Quantum Phases of Matter with Quantum Convolutional Neural Networks
• Analyzing non-equilibrium quantum states through snapshots with artificial neural networks
• Role of stochastic noise and generalization error in the time propagation of neural-network quantum states
• Absorbing phase transition with a continuously varying exponent in a quantum contact process: a neural network approach
• Revealing quantum chaos with machine learning
• An unsupervised deep learning algorithm for single-site reconstruction in quantum gas microscopes
• A perspective on machine learning and data science for strongly correlated electron problems
• Quantum kernels to learn the phases of quantum matter
• Interpretable and unsupervised phase classification
• Z2 parton phases in the mixed-dimensional $t-J_z$ model
• Nonequilibrium Hole Dynamics in Antiferromagnets: Damped Strings and Polarons
• Dominant fifth-order correlations in doped quantum anti-ferromagnets
• Snapshot based characterization of particle currents and the Hall response in synthetic flux lattices
• Deep Learning-Assisted Classification of Site-Resolved Quantum Gas Microscope Images
• Machine-Learned Phase Diagrams of Generalized Kitaev Honeycomb Magnets
• Active Learning Algorithm for Computational Physics
• Certification of quantum states with hidden structure of their bitstrings
• Machine Learning Microscopic Form of Nematic Order in twisted double-bilayer graphene
• Distinguishing an Anderson Insulator from a Many-Body Localized phase through space-time snapshots with Neural Networks
• Phase diagram for strong-coupling Bose polarons
• Skyrmion Ground States of Rapidly Rotating Few-Fermion Systems
• Mapping out phase diagrams with generative classifiers
• Replacing neural networks by optimal analytical predictors for the detection of phase transitions
• From "Weak" to "Strong" Hole Confinement in a Mott Insulator
• Quantifying hole-motion-induced frustration in doped antiferromagnets by Hamiltonian reconstruction
• Optical lattice experiments at unobserved conditions and scales through generative adversarial deep learning
• Experimental demonstration of adversarial examples in learning topological phases
• Phonon-induced pairing in quantum dot quantum simulator
• Exploration of lattice Hamiltonians for functional and structural discovery via Gaussian Process-based Exploration-Exploitation
• Thermometry of one-dimensional Bose gases with neural networks
• Learning entanglement breakdown as a phase transition by confusion
• A comparative study of deconvolution techniques for quantum-gas microscope images
• Quantum entanglement recognition
• Machine learning for structure-property relationships: Scalability and limitations
• Morphology of three-body quantum states from machine learning
• Feshbach hypothesis of high-Tc superconductivity in cuprates
• Observing a topological phase transition with deep neural networks from experimental images of ultracold atoms
• Unsupervised Interpretable Learning of Phases From Many-Qubit Systems
• Vortex detection in atomic Bose-Einstein condensates using neural networks trained on synthetic images
• Adversarial Machine Learning Phases of Matter
• Learning phase transitions from regression uncertainty: A new regression-based machine learning approach for automated detection of phases of matter
• The Coming Decades of Quantum Simulation
• Unsupervised Machine Learning of Quenched Gauge Symmetries: A Proof-of-Concept Demonstration
• Detecting composite orders in layered models via machine learning
• Machine Learning Identification of Impurities in the STM Images
• Scattering theory of mesons in doped antiferromagnetic Mott insulators: Multichannel perspective and Feshbach resonance
• Efficient and quantum-adaptive machine learning with fermion neural networks
• Two-dopant origin of competing stripe and pair formation in Hubbard and $t$-$J$ models
• Learning by Confusion: The Phase Diagram of the Holstein Model
• A learning algorithm with emergent scaling behavior for classifying phase transitions
• Machine-learning the spectral function of a hole in a quantum antiferromagnet
• Kinetic magnetism in the crossover between the square and triangular lattice Fermi-Hubbard models
• Characterization of photoexcited states in the half-filled one-dimensional extended Hubbard model assisted by machine learning
• Extracting Off-Diagonal Order from Diagonal Basis Measurements
• Inferring Hidden Symmetries of Exotic Magnets from Detecting Explicit Order Parameters
• Preparing Quantum States by Measurement-feedback Control with Bayesian Optimization
• Fluctuation based interpretable analysis scheme for quantum many-body snapshots
• Sampling Electronic Fock States using Determinant Quantum Monte Carlo
• Many-body mobility edges in 1D and 2D revealed by convolutional neural networks
• Phonon state tomography of electron correlation dynamics in optically excited solids
• Structural complexity of snapshots of 2D Fermi-Hubbard systems
• Spatial structure of magnetic polarons in strongly interacting antiferromagnets
• Unit-density SU(3) Fermi-Hubbard Model with Spin Flavor Imbalance
• Interpretable machine-learning identification of the crossover from subradiance to superradiance in an atomic array
• Heuristic machinery for thermodynamic studies of SU(N) fermions with neural networks
• Optimized Gutzwiller Projected States for Doped Antiferromagnets in Fermi-Hubbard Simulators
• Optimized Observable Readout from Single-shot Images of Ultracold Atoms via Machine Learning
• Exact nonequilibrium hole dynamics, magnetic polarons and string excitations in antiferromagnetic Bethe lattices