Quantum Boltzmann Machine

Abstract

Inspired by the success of Boltzmann Machines based on classical Boltzmann distribution, we propose a new machine learning approach based on quantum Boltzmann distribution of a transverse-field Ising Hamiltonian. Due to the non-commutative nature of quantum mechanics, the training process of the Quantum Boltzmann Machine (QBM) can become nontrivial. We circumvent the problem by introducing bounds on the quantum probabilities. This allows us to train the QBM efficiently by sampling. We show examples of QBM training with and without the bound, using exact diagonalization, and compare the results with classical Boltzmann training. We also discuss the possibility of using quantum annealing processors like D-Wave for QBM training and application.

10 pages, 4 figures

References in corpus (3)

• Estimation of effective temperatures in quantum annealers for sampling applications: A case study with possible applications in deep learning
• Tomography and Generative Data Modeling via Quantum Boltzmann Training
• Quantum-Assisted Learning of Hardware-Embedded Probabilistic Graphical Models

Cited by in corpus (175)

• Noisy intermediate-scale quantum (NISQ) algorithms
• Continuous-variable quantum neural networks
• Observation of topological phenomena in a programmable lattice of 1,800 qubits
• Strawberry Fields: A Software Platform for Photonic Quantum Computing
• Differentiable Learning of Quantum Circuit Born Machine
• Is quantum advantage the right goal for quantum machine learning?
• The prospects of quantum computing in computational molecular biology
• Quantum Computing for High-Energy Physics: State of the Art and Challenges. Summary of the QC4HEP Working Group
• Quantum agents in the Gym: a variational quantum algorithm for deep Q-learning
• Demonstration of a scaling advantage for a quantum annealer over simulated annealing
• Efficient partition of integer optimization problems with one-hot encoding
• QuantumNAS: Noise-Adaptive Search for Robust Quantum Circuits
• Quantum Hopfield neural network
• The 2021 Quantum Materials Roadmap
• Quantum Variational Autoencoder
• Machine Learning for Quantum Matter
• Quantum Adversarial Machine Learning
• Probing the Universality of Topological Defect Formation in a Quantum Annealer: Kibble-Zurek Mechanism and Beyond
• Power of Pausing: Advancing Understanding of Thermalization in Experimental Quantum Annealers
• An efficient quantum algorithm for the time evolution of parameterized circuits
• Quantum neuromorphic computing
• Hybrid Quantum-Classical Generative Adversarial Network for High Resolution Image Generation
• Quantum Computation Based on Quantum Adiabatic Bifurcations of Kerr-Nonlinear Parametric Oscillators
• Quantum Machine Learning in High Energy Physics
• Quantum Neural Network States: A Brief Review of Methods and Applications
• Simultaneous Perturbation Stochastic Approximation of the Quantum Fisher Information
• Improving solutions by embedding larger subproblems in a D-Wave quantum annealer
• Universal discriminative quantum neural networks
• Enhancing Generative Models via Quantum Correlations
• Scaling and diabatic effects in quantum annealing with a D-Wave device
• Simulation complexity of open quantum dynamics: Connection with tensor networks
• Multiclass classification using quantum convolutional neural networks with hybrid quantum-classical learning
• Adversarial quantum circuit learning for pure state approximation
• Clustering of conditional mutual information for quantum Gibbs states above a threshold temperature
• Neural network representation of tensor network and chiral states
• Demonstration of nonstoquastic Hamiltonian in coupled superconducting flux qubits
• Improved thermal area law and quasi-linear time algorithm for quantum Gibbs states
• Reconstructing quantum states with quantum reservoir networks
• Basic Elements for Simulations of Standard Model Physics with Quantum Annealers: Multigrid and Clock States
• Generative quantum machine learning via denoising diffusion probabilistic models
• Robust quantum compilation and circuit optimisation via energy minimisation
• Quantum enhancements for deep reinforcement learning in large spaces
• Markovian Quantum Neuroevolution for Machine Learning
• The Presence and Absence of Barren Plateaus in Tensor-network Based Machine Learning
• Hybrid quantum-classical machine learning for generative chemistry and drug design
• Quantum machine learning and quantum biomimetics: A perspective
• Training and Classification using a Restricted Boltzmann Machine on the D-Wave 2000Q
• Benchmarking neural networks for quantum computation
• Matrix Product Operators for Sequence to Sequence Learning
• Scalable Emulation of Sign-Problem$-$Free Hamiltonians with Room Temperature p-bits
• Unsupervised learning universal critical behavior via the intrinsic dimension
• Quantum Machine Learning for Finance
• Drawing Phase Diagrams of Random Quantum Systems by Deep Learning the Wave Functions
• Quantum search with hybrid adiabatic-quantum walk algorithms and realistic noise
• Towards Feature Selection for Ranking and Classification Exploiting Quantum Annealers
• Quantum Machine-Learning for Eigenstate Filtration in Two-Dimensional Materials
• Travel time optimization on multi-AGV routing by reverse annealing
• Finding spin-glass ground states using quantum walks
• Expressibility and trainability of parameterized analog quantum systems for machine learning applications
• ResQNets: A Residual Approach for Mitigating Barren Plateaus in Quantum Neural Networks
• Predicting Gibbs-State Expectation Values with Pure Thermal Shadows
• Benchmark test of Black-box optimization using D-Wave quantum annealer
• A Framework for Demonstrating Practical Quantum Advantage: Racing Quantum against Classical Generative Models
• Entanglement guided search for parent Hamiltonians
• Programmable Quantum Annealers as Noisy Gibbs Samplers
• Mean field analysis of reverse annealing for code-division multiple-access multiuser detection
• Quantum many-body systems in thermal equilibrium
• Interpretable Quantum Advantage in Neural Sequence Learning
• Hessian-based optimization of constrained quantum control
• Quantum neural networks to simulate many-body quantum systems
• High-quality Thermal Gibbs Sampling with Quantum Annealing Hardware
• Improved Boltzmann machines with error corrected quantum annealing
• Quantum Capsule Networks
• Supervised learning of time-independent Hamiltonians for gate design
• Quantum computing model of an artificial neuron with continuously valued input data
• Machine Learning and Quantum Devices
• Exact representations of many body interactions with RBM neural networks
• Tight and Efficient Gradient Bounds for Parameterized Quantum Circuits
• Boltzmann machine learning with a variational quantum algorithm
• Quantum adiabatic machine learning with zooming
• Entanglement-based quantum deep learning
• Quantum algorithms for training Gaussian Processes
• Machine learning effective models for quantum systems
• Quantum Quantile Mechanics: Solving Stochastic Differential Equations for Generating Time-Series
• Networked Quantum Services
• Quantum algorithms for scientific computing
• Practical designs for permutation symmetric problem Hamiltonians on hypercubes
• High-Dimensional Similarity Search with Quantum-Assisted Variational Autoencoder
• Perils of Embedding for Sampling Problems
• Benefits of Open Quantum Systems for Quantum Machine Learning
• Symmetries of the squeeze-driven Kerr oscillator
• Learned Optimizers for Analytic Continuation
• Comparing the effects of Boltzmann machines as associative memory in Generative Adversarial Networks between classical and quantum sampling
• Estimating the Density of States of Frustrated Spin Systems
• Quantum correlation alignment for unsupervised domain adaptation
• Efficient Algorithm for Binary Quadratic Problem by Column Generation and Quantum Annealing
• Quantum Continual Learning Overcoming Catastrophic Forgetting
• Virtual Screening of Chemical Space based on Quantum Annealing
• Guided quantum walk
• Simulation of a Variational Quantum Perceptron using Grover's Algorithm
• Tensor-network study of quantum phase transition on Sierpiński fractal
• Experimental demonstration of quantum learning speed-up with classical input data
• Opportunities and challenges of quantum computing for climate modelling
• Dissipative variational quantum algorithms for Gibbs state preparation
• Accelerated Continuous time quantum Monte Carlo method with Machine Learning
• Near-Term Quantum-Classical Associative Adversarial Networks
• Defence against adversarial attacks using classical and quantum-enhanced Boltzmann machines
• Implementation of quantum stochastic walks for function approximation, two-dimensional data classification, and sequence classification
• Automatic design of Hamiltonians
• Quantum-enhanced learning of rotations about an unknown direction
• A QUBO model of the RNA folding problem optimized by variational hybrid quantum annealing
• Quantum DeepONet: Neural operators accelerated by quantum computing
• Exploration of new chemical materials using black-box optimization with the D-wave quantum annealer
• Quantum subspace alignment for domain adaptation
• Towards Transfer Learning for Large-Scale Image Classification Using Annealing-based Quantum Boltzmann Machines
• Hybrid Optimization Method Using Simulated-Annealing-Based Ising Machine and Quantum Annealer
• Perils of Embedding for Quantum Sampling
• Training Quantum Boltzmann Machines with the $\beta$-Variational Quantum Eigensolver
• Machine learning algorithms based on generalized Gibbs ensembles
• Implementing perceptron models with qubits
• Efficient quantum and simulated annealing of Potts models using a half-hot constraint
• Efficient training of energy-based models via spin-glass control
• Hybrid Algorithm of Linear Programming Relaxation and Quantum Annealing
• Dynamical process of a bit-width reduced Ising model with simulated annealing
• Message-passing algorithm of quantum annealing with nonstoquastic Hamiltonian
• Individual subject evaluated difficulty of adjustable mazes generated using quantum annealing
• Predicting quantum many-body dynamics with transferable neural networks
• Geometry and symmetry in quantum Boltzmann machine
• Polynomial Time Quantum Gibbs Sampling for Fermi-Hubbard Model at any Temperature
• Quantum Kernel Evaluation via Hong-Ou-Mandel Interference
• Online calibration scheme for training restricted Boltzmann machines with quantum annealing
• Thermal Area Law for Lattice Bosons
• Storage and retrieval of von Neumann measurements
• On Quantum Circuits for Discrete Graphical Models
• Implementing arbitrary quantum operations via quantum walks on a cycle graph
• QSlack: A slack-variable approach for variational quantum semi-definite programming
• Error-mitigated photonic quantum circuit Born machine
• Liouvillian skin effect in quantum neural networks
• Quantum Inception Score
• Quantum information criteria for model selection in quantum state estimation
• Maximum-Likelihood-Estimate Hamiltonian learning via efficient and robust quantum likelihood gradient
• Quadratic Quantum Speedup for Perceptron Training
• Demonstration of error-suppressed quantum annealing via boundary cancellation
• Contextual Quantum Neural Networks for Stock Price Prediction
• A general learning scheme for classical and quantum Ising machines
• Discriminating Non-Isomorphic Graphs with an Experimental Quantum Annealer
• Multidimensional Quantum Generative Modeling by Quantum Hartley Transform
• Unitary Evolutions Sourced By Interacting Quantum Memories: Closed Quantum Systems Directing Themselves Using Their State Histories
• Subgradient Method using Quantum Annealing for Inequality-Constrained Binary Optimization Problems
• Emergent Equilibrium in All-Optical Single Quantum-Trajectory Ising Machines
• Sampling Problems on a Quantum Computer
• Learning-Driven Annealing with Adaptive Hamiltonian Modification for Solving Large-Scale Problems on Quantum Devices
• Quantum Annealing for Semi-Supervised Learning
• Evolved Quantum Boltzmann Machines
• Understanding and eliminating spurious modes in variational Monte Carlo using collective variables
• Multi-target quantum compilation algorithm
• Optimization of Connection Patterns between Mobile Phones and Base Stations using Quantum Annealing
• Variational Quantum Algorithms for Gibbs State Preparation
• Efficiency of neural-network state representations of one-dimensional quantum spin systems
• Hyperspectral image segmentation with a machine learning model trained using quantum annealer
• Subsampling Factorization Machine Annealing
• Efficient Construction of Feasible Solutions in Column Generation using Quantum Annealing
• Quantum Machine Learning for Climate Modelling
• Efficient inference in the transverse field Ising model
• Natural gradient and parameter estimation for quantum Boltzmann machines
• Efficient bit encoding of neural networks for Fock states
• Quantum generative classification with mixed states
• Training Hybrid Classical-Quantum Classifiers via Stochastic Variational Optimization
• Constrained free energy minimization for the design of thermal states and stabilizer thermodynamic systems
• Noise-Resilient Quantum Reinforcement Learning
• Classical Neural Networks on Quantum Devices via Tensor Network Disentanglers: A Case Study in Image Classification
• Quantum approximate optimization of finite-state bosonic systems
• Quantum annealing and condensed matter physics
• Quantum-classical simulation of quantum field theory by quantum circuit learning
• Learning disentangled representation for classical models