Near-Term Quantum-Classical Associative Adversarial Networks

Abstract

We introduce a new hybrid quantum-classical adversarial machine learning architecture called a quantum-classical associative adversarial network (QAAN). This architecture consists of a classical generative adversarial network with a small auxiliary quantum Boltzmann machine that is simultaneously trained on an intermediate layer of the discriminator of the generative network. We numerically study the performance of QAANs compared to their classical counterparts on the MNIST and CIFAR-10 data sets, and show that QAANs attain a higher quality of learning when evaluated using the Inception score and the Fréchet Inception distance. As the QAAN architecture only relies on sampling simple local observables of a small quantum Boltzmann machine, this model is particularly amenable for implementation on the current and next generations of quantum devices.

arXiv comment11 pages, 9 figures

References in corpus (37)

• Adam: A Method for Stochastic Optimization
• Quantum Computing in the NISQ era and beyond
• Quantum Machine Learning
• A variational eigenvalue solver on a quantum processor
• Quantum algorithm for solving linear systems of equations
• Hardware-efficient Variational Quantum Eigensolver for Small Molecules and Quantum Magnets
• Probing many-body dynamics on a 51-atom quantum simulator
• The theory of variational hybrid quantum-classical algorithms
• Quantum support vector machine for big data classification
• A Quantum Approximate Optimization Algorithm
• Quantum principal component analysis
• NIPS 2016 Tutorial: Generative Adversarial Networks
• Characterizing Quantum Supremacy in Near-Term Devices
• Quantum thermalization through entanglement in an isolated many-body system
• Observation of a Many-Body Dynamical Phase Transition with a 53-Qubit Quantum Simulator
• Wasserstein GAN
• Quantum generative adversarial learning
• Quantum algorithms for supervised and unsupervised machine learning
• Quantum generative adversarial networks
• A blueprint for demonstrating quantum supremacy with superconducting qubits
• Continuous-variable quantum neural networks
• Quantum Boltzmann Machine
• Opportunities and challenges for quantum-assisted machine learning in near-term quantum computers
• A Note on the Inception Score
• Quantum Hopfield neural network
• Tomography and Generative Data Modeling via Quantum Boltzmann Training
• Quantum Variational Autoencoder
• Searching for quantum speedup in quasistatic quantum annealers
• Quantum adiabatic machine learning
• Many Paths to Equilibrium: GANs Do Not Need to Decrease a Divergence At Every Step
• Population Annealing with Weighted Averages: A Monte Carlo Method for Rough Free Energy Landscapes
• Quantum-assisted Helmholtz machines: A quantum-classical deep learning framework for industrial datasets in near-term devices
• Generative training of quantum Boltzmann machines with hidden units
• Robust Classification with Adiabatic Quantum Optimization
• Quantum Language Processing
• Associative Adversarial Networks
• Realizing Quantum Boltzmann Machines Through Eigenstate Thermalization

Cited by in corpus (5)

• Anomaly detection with variational quantum generative adversarial networks
• Interpretable Quantum Advantage in Neural Sequence Learning
• Quantum-assisted associative adversarial network: Applying quantum annealing in deep learning
• Comparing the effects of Boltzmann machines as associative memory in Generative Adversarial Networks between classical and quantum sampling
• ORQVIZ: Visualizing High-Dimensional Landscapes in Variational Quantum Algorithms