Designing quantum many-body matter with conditional generative adversarial networks

Abstract

The computation of dynamical correlators of quantum many-body systems represents an open critical challenge in condensed matter physics. While powerful methodologies have risen in recent years, covering the full parameter space remains unfeasible for most many-body systems with a complex configuration space. Here we demonstrate that conditional Generative Adversarial Networks (GANs) allow simulating the full parameter space of several many-body systems, accounting both for controlled parameters, and stochastic disorder effects. After training with a restricted set of noisy many-body calculations, the conditional GAN algorithm provides the whole dynamical excitation spectra for a Hamiltonian instantly and with an accuracy analogous to the exact calculation. We further demonstrate how the trained conditional GAN automatically provides a powerful method for Hamiltonian learning from its dynamical excitations, and to flag non-physical systems via outlier detection. Our methodology puts forward generative adversarial learning as a powerful technique to explore complex many-body phenomena, providing a starting point to design large-scale quantum many-body matter.

References in corpus (61)

• The density-matrix renormalization group in the age of matrix product states
• The density-matrix renormalization group
• Correlated Electrons in High Temperature Superconductors
• Machine learning and the physical sciences
• Solving the Quantum Many-Body Problem with Artificial Neural Networks
• Quantum Spin Liquids
• Matrix Product States, Projected Entangled Pair States, and variational renormalization group methods for quantum spin systems
• Machine learning phases of matter
• Entanglement spectrum of a topological phase in one dimension
• One-Dimensional Fermi liquids
• The Kernel Polynomial Method
• Tensor-Entanglement-Filtering Renormalization Approach and Symmetry Protected Topological Order
• Classification of Gapped Symmetric Phases in 1D Spin Systems
• Symmetry protection of topological order in one-dimensional quantum spin systems
• Learning phase transitions by confusion
• Stripe order in the underdoped region of the two-dimensional Hubbard model
• Herbertsmithite and the Search for the Quantum Spin Liquid
• Solutions of the Two Dimensional Hubbard Model: Benchmarks and Results from a Wide Range of Numerical Algorithms
• Learning Particle Physics by Example: Location-Aware Generative Adversarial Networks for Physics Synthesis
• Dynamical Correlation Functions using the Density Matrix Renormalization Group
• Observation of fractional edge excitations in nanographene spin chains
• Accelerating Science with Generative Adversarial Networks: An Application to 3D Particle Showers in Multi-Layer Calorimeters
• Identifying topological order through unsupervised machine learning
• Does a single eigenstate encode the full Hamiltonian?
• Experimental Quantum Hamiltonian Learning
• Machine Learning Phases of Strongly Correlated Fermions
• Theory of Quantum Corrals and Quantum Mirages
• Hamiltonian Learning and Certification Using Quantum Resources
• Colloquium: Atomic spin chains on surfaces
• Theory of single spin inelastic tunneling spectroscopy
• Generative Adversarial Networks and Perceptual Losses for Video Super-Resolution
• Unsupervised machine learning and band topology
• Machine Learning for Quantum Matter
• Atomic spin chain realization of a model for quantum criticality
• Integrating Neural Networks with a Quantum Simulator for State Reconstruction
• Machine-learning-assisted correction of correlated qubit errors in a topological code
• Spin wave imaging in atomically designed nanomagnets
• Engineering the eigenstates of coupled spin-1/2 atoms on a surface
• Neural Network-based Classification of Crystal Symmetries from X-Ray Diffraction Patterns
• Local control of single atom magneto-crystalline anisotropy
• Chebyshev Matrix Product State Impurity Solver for the Dynamical Mean-Field Theory
• Chebyshev expansion for Impurity Models using Matrix Product States
• Computational inverse method for constructing spaces of quantum models from wave functions
• Quantum Hamiltonian Learning Using Imperfect Quantum Resources
• Hamiltonian Tomography via Quantum Quench
• Tuning Single-Atom Electron Spin Resonance in a Vector-Magnetic Field
• Unsupervised identification of topological order using predictive models
• Neural network decoder for topological color codes with circuit level noise
• Real space mapping of topological invariants using artificial neural networks
• Hamiltonian Learning for Quantum Error Correction
• Learning phase transitions from dynamics
• Scalable Hamiltonian learning for large-scale out-of-equilibrium quantum dynamics
• Analyzing non-equilibrium quantum states through snapshots with artificial neural networks
• Topological spin excitations in Harper-Heisenberg spin chains
• Machine Learning for Continuous Quantum Error Correction on Superconducting Qubits
• Supervised learning in Hamiltonian reconstruction from local measurements on eigenstates
• Chebyshev expansion of spectral functions using restricted Boltzmann machines
• Inducing a many-body topological state of matter through Coulomb-engineered local interactions
• Solitonic in-gap modes in a superconductor-quantum antiferromagnet interface
• Dynamical topological excitations in parafermion chains
• Neural network enhanced hybrid quantum many-body dynamical distributions

Cited by in corpus (8)

• Adversarial Hamiltonian learning of quantum dots in a minimal Kitaev chain
• Hamiltonian inference from dynamical excitations in confined quantum magnets
• Hamiltonian learning with real-space impurity tomography in topological moire superconductors
• Machine learning the Kondo entanglement cloud from local measurements
• Transfer learning from Hermitian to non-Hermitian quantum many-body physics
• Hamiltonian-learning quantum magnets with non-local impurity tomography
• Hamiltonian Learning of Triplon Excitations in an Artificial Nanoscale Molecular Quantum Magnet
• Machine-learning-enabled characterization of individual ring resonators in integrated photonic lattices