Exponentially improved efficient machine learning for quantum many-body states with provable guarantees

Abstract

Solving the ground state and the ground-state properties of quantum many-body systems is generically a hard task for classical algorithms. For a family of Hamiltonians defined on an $m$-dimensional space of physical parameters, the ground state and its properties at an arbitrary parameter configuration can be predicted via a machine learning protocol up to a prescribed prediction error $\epsilon$, provided that a sample set (of size $N$) of the states can be efficiently prepared and measured. In a recent work [Huang et al., Science 377, eabk3333 (2022)], a rigorous guarantee for such a generalization was proved. Unfortunately, an exponential scaling for the provable sample complexity, $N=m^{\mathcal{O}\left(\frac{1}{\epsilon }\right)}$, was found to be universal for generic gapped Hamiltonians. This result applies to the situation where the dimension of the parameter space is large while the scaling with the accuracy is not an urgent factor. In this work, we consider an alternative scenario where $m$ is a finite, not necessarily large constant while the scaling with the prediction error becomes the central concern. By jointly preserving the fundamental properties of density matrices in the learning protocol and utilizing the continuity of quantum states in the parameter range of interest, we rigorously obtain a polynomial sample complexity for predicting quantum many-body states and their properties, with respect to the uniform prediction error $\epsilon$ and the number of qubits $n$. Moreover, if restricted to learning local quantum-state properties, the number of samples with respect to $n$ can be further reduced exponentially. Our results provide theoretical guarantees for efficient learning of quantum many-body states and their properties, with model-independent applications not restricted to ground states of gapped Hamiltonians.

Published on Physical Review Research 6, 033035 (2024)

References in corpus (91)

• Quantum Machine Learning
• Quantum Simulation
• Machine learning and the physical sciences
• Solving the Quantum Many-Body Problem with Artificial Neural Networks
• Adiabatic Quantum Computing
• Quantum Chemistry in the Age of Quantum Computing
• Machine learning phases of matter
• An introduction to quantum machine learning
• Predicting Many Properties of a Quantum System from Very Few Measurements
• Quantum state tomography via compressed sensing
• Fermionic quantum computation
• A high-bias, low-variance introduction to Machine Learning for physicists
• Quantum spin squeezing
• Learning phase transitions by confusion
• Quantum Fisher information matrix and multiparameter estimation
• Discovering Phase Transitions with Unsupervised Learning
• Unsupervised learning of phase transitions: from principal component analysis to variational autoencoders
• Quantum Tomography via Compressed Sensing: Error Bounds, Sample Complexity, and Efficient Estimators
• Machine learning quantum phases of matter beyond the fermion sign problem
• Discovering Phases, Phase Transitions and Crossovers through Unsupervised Machine Learning: A critical examination
• Efficient Representation of Quantum Many-body States with Deep Neural Networks
• Machine Learning Topological States
• Neural-Network Approach to Dissipative Quantum Many-Body Dynamics
• Identifying topological order through unsupervised machine learning
• Quantum Loop Topography for Machine Learning
• Machine Learning Topological Invariants with Neural Networks
• Deep autoregressive models for the efficient variational simulation of many-body quantum systems
• Machine Learning Phases of Strongly Correlated Fermions
• Symmetries and many-body excited states with neural-network quantum states
• Equivalence of restricted Boltzmann machines and tensor network states
• Provably efficient machine learning for quantum many-body problems
• Variational Quantum Monte Carlo Method with a Neural-Network Ansatz for Open Quantum Systems
• Identifying Quantum Phase Transitions using Artificial Neural Networks on Experimental Data
• Variational neural network ansatz for steady states in open quantum systems
• Efficient estimation of Pauli observables by derandomization
• Constructing neural stationary states for open quantum many-body systems
• Experimental neural network enhanced quantum tomography
• Machine learning vortices at the Kosterlitz-Thouless transition
• Unsupervised machine learning and band topology
• Experimental Machine Learning of Quantum States
• Unsupervised machine learning account of magnetic transitions in the Hubbard model
• Machine learning meets quantum physics
• Automorphic Equivalence within Gapped Phases of Quantum Lattice Systems
• Machine learning out-of-equilibrium phases of matter
• Kernel methods for interpretable machine learning of order parameters
• Deep Learning the Quantum Phase Transitions in Random Two-Dimensional Electron Systems
• Identifying Quantum Phase Transitions with Adversarial Neural Networks
• Machine learning of phase transitions in the percolation and XY models
• Discriminative Cooperative Networks for Detecting Phase Transitions
• Machine learning of quantum phase transitions
• Unsupervised Manifold Clustering of Topological Phononics
• Topological quantum phase transitions retrieved through unsupervised machine learning
• Unveiling phase transitions with machine learning
• Machine learning assisted quantum state estimation
• Reinforcement Learning for Many-Body Ground-State Preparation Inspired by Counterdiabatic Driving
• Neural network quantum state tomography in a two-qubit experiment
• Deep Learning Topological Invariants of Band Insulators
• Learning Disordered Topological Phases by Statistical Recovery of Symmetry
• Machine Learning Topological Phases with a Solid-state Quantum Simulator
• Unsupervised identification of topological order using predictive models
• Learning multiple order parameters with interpretable machines
• Unsupervised machine learning of quantum phase transitions using diffusion maps
• Transfer learning for scalability of neural-network quantum states
• Matrix Model simulations using Quantum Computing, Deep Learning, and Lattice Monte Carlo
• Approximate Autonomous Quantum Error Correction with Reinforcement Learning
• Machine Learning as a universal tool for quantitative investigations of phase transition
• Automated discovery of characteristic features of phase transitions in many-body localization
• Solving Quasiparticle Band Spectra of Real Solids using Neural-Network Quantum States
• Unsupervised Learning of Non-Hermitian Topological Phases
• Unsupervised learning universal critical behavior via the intrinsic dimension
• Drawing Phase Diagrams of Random Quantum Systems by Deep Learning the Wave Functions
• Divergence of predictive model output as indication of phase transitions
• XY model on the circle: diagonalization, spectrum, and forerunners of the quantum phase transition
• Eigenstate extraction with neural-network tomography
• Improved machine learning algorithm for predicting ground state properties
• Purifying Deep Boltzmann Machines for Thermal Quantum States
• Unsupervised learning using topological data augmentation
• Intrinsic dimension of path integrals: data mining quantum criticality and emergent simplicity
• Variational autoencoder reconstruction of complex many-body physics
• Approximating power of machine-learning ansatz for quantum many-body states
• Identifying Product Order with Restricted Boltzmann Machines
• Supervised learning for robust quantum control in composite-pulse systems
• Generalized Coherent States, Reproducing Kernels, and Quantum Support Vector Machines
• Gaussian Process States: A data-driven representation of quantum many-body physics
• Anomalous behavior of the energy gap in the one-dimensional quantum XY model
• Multiqubit matter-wave interferometry under decoherence and the Heisenberg scaling recovery
• Unsupervised Learning Eigenstate Phases of Matter
• Estimating the Euclidean quantum propagator with deep generative modeling of Feynman paths
• Probing Criticality in Quantum Spin Chains with Neural Networks
• Identifying topology of leaky photonic lattices with machine learning
• Ground-state properties via machine learning quantum constraints

Cited by in corpus (6)

• Machine learning on quantum experimental data toward solving quantum many-body problems
• Efficient Learning for Linear Properties of Bounded-Gate Quantum Circuits
• Predicting topological invariants and unconventional superconducting pairing from density of states and machine learning
• Quantum circuit complexity and unsupervised machine learning of topological order
• Efficient Learning of Long-Range and Equivariant Quantum Systems
• Critical Scaling of the Quantum Wasserstein Distance