Variational inference with a quantum computer

Abstract

Inference is the task of drawing conclusions about unobserved variables given observations of related variables. Applications range from identifying diseases from symptoms to classifying economic regimes from price movements. Unfortunately, performing exact inference is intractable in general. One alternative is variational inference, where a candidate probability distribution is optimized to approximate the posterior distribution over unobserved variables. For good approximations, a flexible and highly expressive candidate distribution is desirable. In this work, we use quantum Born machines as variational distributions over discrete variables. We apply the framework of operator variational inference to achieve this goal. In particular, we adopt two specific realizations: one with an adversarial objective and one based on the kernelized Stein discrepancy. We demonstrate the approach numerically using examples of Bayesian networks, and implement an experiment on an IBM quantum computer. Our techniques enable efficient variational inference with distributions beyond those that are efficiently representable on a classical computer.

arXiv comment17 pages, 9 figures, 1 table; As published in Phys. Rev. Applied

References in corpus (79)

• Auto-Encoding Variational Bayes
• Supplementary information for "Quantum supremacy using a programmable superconducting processor"
• Variational Inference: A Review for Statisticians
• Categorical Reparameterization with Gumbel-Softmax
• MCMC using Hamiltonian dynamics
• Supervised learning with quantum enhanced feature spaces
• Stochastic Backpropagation and Approximate Inference in Deep Generative Models
• Barren plateaus in quantum neural network training landscapes
• Quantum machine learning in feature Hilbert spaces
• Quantum Circuit Learning
• Variational Inference with Normalizing Flows
• Characterizing Quantum Supremacy in Near-Term Devices
• Strong quantum computational advantage using a superconducting quantum processor
• Parameterized quantum circuits as machine learning models
• Cost Function Dependent Barren Plateaus in Shallow Parametrized Quantum Circuits
• Evaluating analytic gradients on quantum hardware
• The Concrete Distribution: A Continuous Relaxation of Discrete Random Variables
• The power of quantum neural networks
• Noise-Induced Barren Plateaus in Variational Quantum Algorithms
• The effect of data encoding on the expressive power of variational quantum machine learning models
• Power of data in quantum machine learning
• Data re-uploading for a universal quantum classifier
• Connecting ansatz expressibility to gradient magnitudes and barren plateaus
• A rigorous and robust quantum speed-up in supervised machine learning
• Quantum machine learning: a classical perspective
• Quantum generative adversarial networks
• Quantum Generative Adversarial Networks for Learning and Loading Random Distributions
• t$|$ket$⟩$ : A Retargetable Compiler for NISQ Devices
• A generative modeling approach for benchmarking and training shallow quantum circuits
• Absence of Barren Plateaus in Quantum Convolutional Neural Networks
• Robust data encodings for quantum classifiers
• Quantum speedup of Monte Carlo methods
• The Expressive Power of Parameterized Quantum Circuits
• Average-case complexity versus approximate simulation of commuting quantum computations
• Quantum Supremacy and the Complexity of Random Circuit Sampling
• Differentiable Learning of Quantum Circuit Born Machine
• Information-theoretic bounds on quantum advantage in machine learning
• Unsupervised Generative Modeling Using Matrix Product States
• Concrete Categorical Model of a Quantum Circuit Description Language with Measurement
• Estimation of effective temperatures in quantum annealers for sampling applications: A case study with possible applications in deep learning
• Training of Quantum Circuits on a Hybrid Quantum Computer
• Demonstration of quantum advantage in machine learning
• Application of Quantum Annealing to Training of Deep Neural Networks
• Quantum Variational Autoencoder
• Quantum generative adversarial network for generating discrete distribution
• The Born Supremacy: Quantum Advantage and Training of an Ising Born Machine
• Variational Thermal Quantum Simulation via Thermofield Double States
• Quantum-Assisted Learning of Hardware-Embedded Probabilistic Graphical Models
• Quantum Inference on Bayesian Networks
• Information Perspective to Probabilistic Modeling: Boltzmann Machines versus Born Machines
• Measuring Analytic Gradients of General Quantum Evolution with the Stochastic Parameter Shift Rule
• Quantum-assisted Helmholtz machines: A quantum-classical deep learning framework for industrial datasets in near-term devices
• Learning and Inference on Generative Adversarial Quantum Circuits
• Bayesian Network Structure Learning Using Quantum Annealing
• On the Quantum versus Classical Learnability of Discrete Distributions
• Enhancing Generative Models via Quantum Correlations
• Adversarial quantum circuit learning for pure state approximation
• Analyzing the barren plateau phenomenon in training quantum neural networks with the ZX-calculus
• Automated Variational Inference in Probabilistic Programming
• Quantum Bayesian Nets
• Reformulation of the No-Free-Lunch Theorem for Entangled Data Sets
• Anomaly detection with variational quantum generative adversarial networks
• Quantum Hamiltonian-Based Models and the Variational Quantum Thermalizer Algorithm
• Generative model benchmarks for superconducting qubits
• Quantum Wasserstein Generative Adversarial Networks
• A Variational Quantum Algorithm for Preparing Quantum Gibbs States
• Quantum machine learning and quantum biomimetics: A perspective
• Quantum Commuting Circuits and Complexity of Ising Partition Functions
• Quantum algorithms for classical lattice models
• Quantum Enhanced Inference in Markov Logic Networks
• Quantum-assisted associative adversarial network: Applying quantum annealing in deep learning
• Boltzmann machine learning with a variational quantum algorithm
• Variational quantum Gibbs state preparation with a truncated Taylor series
• Recognition Networks for Approximate Inference in BN20 Networks
• Quantum Annealing for Variational Bayes Inference
• A Quantum Extension of Variational Bayes Inference
• Generation of High-Resolution Handwritten Digits with an Ion-Trap Quantum Computer
• Quantum Annealing for Variational Bayes Inference
• Convergence and Sample Complexity of SGD in GANs

Cited by in corpus (21)

• Quantum Machine Learning: from physics to software engineering
• Near-Term Quantum Computing Techniques: Variational Quantum Algorithms, Error Mitigation, Circuit Compilation, Benchmarking and Classical Simulation
• Barren plateaus in quantum tensor network optimization
• NISQ Computers: A Path to Quantum Supremacy
• Synergy Between Quantum Circuits and Tensor Networks: Short-cutting the Race to Practical Quantum Advantage
• Variational Quantum-Neural Hybrid Eigensolver
• Quantum Machine Learning for Digital Health? A Systematic Review
• Variational quantum amplitude estimation
• Trainability barriers and opportunities in quantum generative modeling
• Quantum Deep Hedging
• A performance characterization of quantum generative models
• Neural network encoded variational quantum algorithms
• Conditional Born machine for Monte Carlo event generation
• Bayesian Learning of Parameterised Quantum Circuits
• F-Divergences and Cost Function Locality in Generative Modelling with Quantum Circuits
• Quantum Advantage in Variational Bayes Inference
• Tensor tree learns hidden relational structures in data to construct generative models
• Variational post-selection for ground states and thermal states simulation
• Variational Inference for Quantum HyperNetworks
• Building Continuous Quantum-Classical Bayesian Neural Networks for a Classical Clinical Dataset
• Modeling Time-Dependent Systems using Dynamic Quantum Bayesian Networks