Tomography and Generative Data Modeling via Quantum Boltzmann Training

Abstract

The promise of quantum neural nets, which utilize quantum effects to model complex data sets, has made their development an aspirational goal for quantum machine learning and quantum computing in general. Here we provide new methods of training quantum Boltzmann machines, which are a class of recurrent quantum neural network. Our work generalizes existing methods and provides new approaches for training quantum neural networks that compare favorably to existing methods. We further demonstrate that quantum Boltzmann machines enable a form of quantum state tomography that not only estimates a state but provides a perscription for generating copies of the reconstructed state. Classical Boltzmann machines are incapable of this. Finally we compare small non-stoquastic quantum Boltzmann machines to traditional Boltzmann machines for generative tasks and observe evidence that quantum models outperform their classical counterparts.

References in corpus (1)

• Quantum Inspired Training for Boltzmann Machines

Cited by in corpus (85)

• Noisy intermediate-scale quantum (NISQ) algorithms
• Quantum computing for finance: overview and prospects
• Quantum machine learning: a classical perspective
• Continuous-variable quantum neural networks
• A generative modeling approach for benchmarking and training shallow quantum circuits
• Differentiable Learning of Quantum Circuit Born Machine
• Opportunities and challenges for quantum-assisted machine learning in near-term quantum computers
• Beyond Barren Plateaus: Quantum Variational Algorithms Are Swamped With Traps
• The prospects of quantum computing in computational molecular biology
• Quantum Hopfield neural network
• Learning a local Hamiltonian from local measurements
• Quantum Machine Learning for Chemistry and Physics
• Quantum principal component analysis only achieves an exponential speedup because of its state preparation assumptions
• Prospects for Quantum Enhancement with Diabatic Quantum Annealing
• Machine learning method for state preparation and gate synthesis on photonic quantum computers
• Quantum computing models for artificial neural networks
• Information Perspective to Probabilistic Modeling: Boltzmann Machines versus Born Machines
• Variational Quantum Boltzmann Machines
• Quantum-assisted Helmholtz machines: A quantum-classical deep learning framework for industrial datasets in near-term devices
• Fast inversion, preconditioned quantum linear system solvers, and fast evaluation of matrix functions
• Clustering of conditional mutual information for quantum Gibbs states above a threshold temperature
• Adversarial quantum circuit learning for pure state approximation
• Local-measurement-based quantum state tomography via neural networks
• Improved thermal area law and quasi-linear time algorithm for quantum Gibbs states
• Hamiltonian Learning for Quantum Error Correction
• Learning the dynamics of open quantum systems from their steady states
• An atomic Boltzmann machine capable of on-chip learning
• A Variational Quantum Algorithm for Preparing Quantum Gibbs States
• Quantum enhancements for deep reinforcement learning in large spaces
• Quantum machine learning and quantum biomimetics: A perspective
• Thermal State Preparation via Rounding Promises
• Rapid thermalization of spin chain commuting Hamiltonians
• Quantum Machine-Learning for Eigenstate Filtration in Two-Dimensional Materials
• Predicting Gibbs-State Expectation Values with Pure Thermal Shadows
• Quantum many-body systems in thermal equilibrium
• Generative training of quantum Boltzmann machines with hidden units
• Machine Learning and Quantum Devices
• On the Sample Complexity of Quantum Boltzmann Machine Learning
• Variational Gibbs State Preparation on NISQ devices
• Tight and Efficient Gradient Bounds for Parameterized Quantum Circuits
• Fragmented imaginary-time evolution for early-stage quantum signal processors
• Reconstructing quantum molecular rotor ground states
• A Practical Introduction to Benchmarking and Characterization of Quantum Computers
• Quantum Language Processing
• Quantum approximate Bayesian computation for NMR model inference
• Entanglement-based quantum deep learning
• Quantum algorithms for scientific computing
• Near-Optimal Quantum Algorithms for Multivariate Mean Estimation
• Benefits of Open Quantum Systems for Quantum Machine Learning
• Quantum State Tomography with Conditional Generative Adversarial Networks
• Variational quantum Gibbs state preparation with a truncated Taylor series
• Variational Approach to Quantum State Tomography based on Maximal Entropy Formalism
• Optimal short-time measurements for Hamiltonian learning
• Machine learning generated configurations in presence of a conserved quantity: a cautionary tale
• Automated Machine Learning can Classify Bound Entangled States with Tomograms
• Near-Term Quantum-Classical Associative Adversarial Networks
• Dissipative variational quantum algorithms for Gibbs state preparation
• Parameterized quantum circuits as universal generative models for continuous multivariate distributions
• Automatic design of Hamiltonians
• Reconstructing effective Hamiltonians from nonequilibrium (pre-)thermal steady states
• Training Quantum Boltzmann Machines with the $\beta$-Variational Quantum Eigensolver
• Machine learning algorithms based on generalized Gibbs ensembles
• Quantum algorithms for multivariate Monte Carlo estimation
• Geometry and symmetry in quantum Boltzmann machine
• Quantum Annealing Machines Based on Semiconductor Nanostructures
• On Quantum Circuits for Discrete Graphical Models
• Quantum information criteria for model selection in quantum state estimation
• Quantum Inception Score
• Group theory on quantum Boltzmann machine
• Systematic comparison of deep belief network training using quantum annealing vs. classical techniques
• Efficient Characterization of Quantum Evolutions via a Recommender System
• Quantum Generative Training Using Rényi Divergences
• Unsupervised Learning of Effective Quantum Impurity Models
• A Parameter-Efficient Quantum Anomaly Detection Method on a Superconducting Quantum Processor
• Evolved Quantum Boltzmann Machines
• Variational Quantum Algorithms for Gibbs State Preparation
• Efficiency of neural-network state representations of one-dimensional quantum spin systems
• Gibbs state sampling via cluster expansions
• Quantum Machine Learning For Classical Data
• Implementation of a Hamming-Distance-Like Genomic Quantum Classifier Using Inner Products on IBMQX4 and IBMQX16
• Natural gradient and parameter estimation for quantum Boltzmann machines
• Variational Quantum Generative Modeling by Sampling Expectation Values of Tunable Observables
• Expressive equivalence of classical and quantum restricted Boltzmann machines
• Constrained free energy minimization for the design of thermal states and stabilizer thermodynamic systems
• Quantum Algorithms in Cybernetics