Quantum generative adversarial networks

Abstract

Quantum machine learning is expected to be one of the first potential general-purpose applications of near-term quantum devices. A major recent breakthrough in classical machine learning is the notion of generative adversarial training, where the gradients of a discriminator model are used to train a separate generative model. In this work and a companion paper, we extend adversarial training to the quantum domain and show how to construct generative adversarial networks using quantum circuits. Furthermore, we also show how to compute gradients -- a key element in generative adversarial network training -- using another quantum circuit. We give an example of a simple practical circuit ansatz to parametrize quantum machine learning models and perform a simple numerical experiment to demonstrate that quantum generative adversarial networks can be trained successfully.

arXiv comment10 pages, 8 figures

References in corpus (22)

• Polynomial-Time Algorithms for Prime Factorization and Discrete Logarithms on a Quantum Computer
• Quantum Machine Learning
• Generative Adversarial Networks: An Overview
• A variational eigenvalue solver on a quantum processor
• Hardware-efficient Variational Quantum Eigensolver for Small Molecules and Quantum Magnets
• An introduction to quantum machine learning
• Quantum fingerprinting
• On the Power of One Bit of Quantum Information
• Quantum optimization using variational algorithms on near-term quantum devices
• Quantum autoencoders for efficient compression of quantum data
• Quantum Simulation of Electronic Structure with Linear Depth and Connectivity
• Learning Particle Physics by Example: Location-Aware Generative Adversarial Networks for Physics Synthesis
• Comparing, Optimising and Benchmarking Quantum Control Algorithms in a Unifying Programming Framework
• Unsupervised Machine Learning on a Hybrid Quantum Computer
• Quantum Neuron: an elementary building block for machine learning on quantum computers
• Generating and designing DNA with deep generative models
• Practical optimization for hybrid quantum-classical algorithms
• A quantum algorithm to train neural networks using low-depth circuits
• The Learnability of Quantum States
• Low-depth circuit ansatz for preparing correlated fermionic states on a quantum computer
• Simultaneous model selection and parameter estimation: A superconducting qubit coupled to a bath of incoherent two-level systems
• Quantum Nash Equilibria and Quantum Computing

Cited by in corpus (184)

• Noisy intermediate-scale quantum (NISQ) algorithms
• Parameterized quantum circuits as machine learning models
• Expressibility and entangling capability of parameterized quantum circuits for hybrid quantum-classical algorithms
• Challenges and Opportunities in Quantum Machine Learning
• Quantum generative adversarial learning
• A rigorous and robust quantum speed-up in supervised machine learning
• Hybrid quantum-classical algorithms and quantum error mitigation
• Generalization in quantum machine learning from few training data
• Quantum Generative Adversarial Networks for Learning and Loading Random Distributions
• Continuous-variable quantum neural networks
• Robust data encodings for quantum classifiers
• Hybrid Quantum-Classical Convolutional Neural Networks
• Experimental Quantum Generative Adversarial Networks for Image Generation
• PennyLane: Automatic differentiation of hybrid quantum-classical computations
• The prospects of quantum computing in computational molecular biology
• Sequential minimal optimization for quantum-classical hybrid algorithms
• Quantum generative adversarial learning in a superconducting quantum circuit
• Quantum generative adversarial network for generating discrete distribution
• Quantum Machine Learning for Chemistry and Physics
• Quantum noise protects quantum classifiers against adversaries
• The Born Supremacy: Quantum Advantage and Training of an Ising Born Machine
• Quantum Adversarial Machine Learning
• Noisy intermediate-scale quantum computers
• Measurements as a roadblock to near-term practical quantum advantage in chemistry: resource analysis
• Quantum computing models for artificial neural networks
• Hybrid Quantum-Classical Generative Adversarial Network for High Resolution Image Generation
• Quantum Machine Learning in High Energy Physics
• Variational Quantum Reinforcement Learning via Evolutionary Optimization
• Theory for Equivariant Quantum Neural Networks
• Quantum Machine Learning: from physics to software engineering
• Variational Quantum Boltzmann Machines
• Early Fault-Tolerant Quantum Computing
• Near-Term Quantum Computing Techniques: Variational Quantum Algorithms, Error Mitigation, Circuit Compilation, Benchmarking and Classical Simulation
• Learning and Inference on Generative Adversarial Quantum Circuits
• Theoretical Guarantees for Permutation-Equivariant Quantum Neural Networks
• Biology and medicine in the landscape of quantum advantages
• Exploring the Advantages of Quantum Generative Adversarial Networks in Generative Chemistry
• On the Quantum versus Classical Learnability of Discrete Distributions
• An end-to-end trainable hybrid classical-quantum classifier
• Adversarial quantum circuit learning for pure state approximation
• Towards quantum enhanced adversarial robustness in machine learning
• Automatic design of quantum feature maps
• QuGAN: A Quantum State Fidelity based Generative Adversarial Network
• Learning quantum data with the quantum Earth Mover's distance
• Benchmarking Adversarially Robust Quantum Machine Learning at Scale
• Anomaly detection with variational quantum generative adversarial networks
• Quantum Hamiltonian-Based Models and the Variational Quantum Thermalizer Algorithm
• Adaptive pruning-based optimization of parameterized quantum circuits
• Generative model benchmarks for superconducting qubits
• Generalization despite overfitting in quantum machine learning models
• Generative quantum machine learning via denoising diffusion probabilistic models
• Experimental quantum kernel machine learning with nuclear spins in a solid
• Reinforcement learning for optimization of variational quantum circuit architectures
• Hybrid quantum-classical machine learning for generative chemistry and drug design
• Realizing a quantum generative adversarial network using a programmable superconducting processor
• Reflection Equivariant Quantum Neural Networks for Enhanced Image Classification
• Quantum unary approach to option pricing
• Variational inference with a quantum computer
• Robust resource-efficient quantum variational ansatz through evolutionary algorithm
• Quantum Machine Learning for Finance
• Style-based quantum generative adversarial networks for Monte Carlo events
• Generative Quantum Learning of Joint Probability Distribution Functions
• Quantum Machine Learning in Drug Discovery: Applications in Academia and Pharmaceutical Industries
• Natural Evolutionary Strategies for Variational Quantum Computation
• Variational Quantum Algorithms for Dimensionality Reduction and Classification
• Hybrid quantum-classical neural network for calculating ground state energies of molecules
• Quantum Architecture Search via Deep Reinforcement Learning
• Quantum-Noise-Driven Generative Diffusion Models
• Quantum semi-supervised generative adversarial network for enhanced data classification
• Analysis of Quantum Approximate Optimization Algorithm under Realistic Noise in Superconducting Qubits
• New Trends in Quantum Machine Learning
• Quantum Monge-Kantorovich problem and transport distance between density matrices
• A brief introduction to quantum algorithms
• Recent Advances in Deep Learning for Channel Coding: A Survey
• Quantum Capsule Networks
• A performance characterization of quantum generative models
• Noise robustness and experimental demonstration of a quantum generative adversarial network for continuous distributions
• An application benchmark for fermionic quantum simulations
• Dual-Parameterized Quantum Circuit GAN Model in High Energy Physics
• A review of Quantum Neural Networks: Methods, Models, Dilemma
• Tight and Efficient Gradient Bounds for Parameterized Quantum Circuits
• Representation of binary classification trees with binary features by quantum circuits
• Hybrid Quantum-Classical Graph Convolutional Network
• A hybrid quantum-classical conditional generative adversarial network algorithm for human-centered paradigm in cloud
• Hybrid quantum-classical classifier based on tensor network and variational quantum circuit
• Reducing the amount of single-qubit rotations in VQE and related algorithms
• Quantum algorithm for credit valuation adjustments
• Quantum Quantile Mechanics: Solving Stochastic Differential Equations for Generating Time-Series
• Squeezing and quantum approximate optimization
• Predominant Aspects on Security for Quantum Machine Learning: Literature Review
• Quantum Generative Adversarial Networks For Anomaly Detection In High Energy Physics
• Quantum Generative Learning for High-Resolution Medical Image Generation
• Networked Quantum Services
• Connecting geometry and performance of two-qubit parameterized quantum circuits
• Quantum gradient descent algorithms for nonequilibrium steady states and linear algebraic systems
• Quantum correlation alignment for unsupervised domain adaptation
• Playing Atari with Hybrid Quantum-Classical Reinforcement Learning
• Statistical Complexity of Quantum Learning
• Boosted Ensembles of Qubit and Continuous Variable Quantum Support Vector Machines for B Meson Flavour Tagging
• Variational quantum state discriminator for supervised machine learning
• Detecting Violations of Differential Privacy for Quantum Algorithms
• How to enhance quantum generative adversarial learning of noisy information
• Opportunities and challenges of quantum computing for climate modelling
• Near-Term Quantum-Classical Associative Adversarial Networks
• Hybrid quantum learning with data re-uploading on a small-scale superconducting quantum simulator
• QDNN: DNN with Quantum Neural Network Layers
• When Federated Learning Meets Quantum Computing: Survey and Research Opportunities
• Optimizing Quantum Convolutional Neural Network Architectures for Arbitrary Data Dimension
• Implementation of quantum stochastic walks for function approximation, two-dimensional data classification, and sequence classification
• Parameterized quantum circuits as universal generative models for continuous multivariate distributions
• Protocols for classically training quantum generative models on probability distributions
• F-Divergences and Cost Function Locality in Generative Modelling with Quantum Circuits
• Quantum subspace alignment for domain adaptation
• Efficient quantum interpolation of natural data
• Quantum generative adversarial learning in photonics
• Quantum Measurement Classification with Qudits
• Generative model for learning quantum ensemble via optimal transport loss
• Protocols for Trainable and Differentiable Quantum Generative Modelling
• Application of the Diamond Gate in Quantum Fourier Transformations and Quantum Machine Learning
• Parametrized constant-depth quantum neuron
• Quantum Generative Adversarial Networks in a Silicon Photonic Chip with Maximum Expressibility
• Traffic Sign Classification Using Deep and Quantum Neural Networks
• Photonic quantum generative adversarial networks for classical data
• Exploration of Quantum Neural Architecture by Mixing Quantum Neuron Designs
• Gradients and frequency profiles of quantum re-uploading models
• Generating Universal Adversarial Perturbations for Quantum Classifiers
• Information flow in parameterized quantum circuits
• Towards AutoQML: A Cloud-Based Automated Circuit Architecture Search Framework
• Application-Oriented Benchmarking of Quantum Generative Learning Using QUARK
• Quantum neural compressive sensing for ghost imaging
• Quantum encoder for fixed Hamming-weight subspaces
• Implementing arbitrary quantum operations via quantum walks on a cycle graph
• Universal noise-precision relations in variational quantum algorithms
• Error-mitigated photonic quantum circuit Born machine
• Precise Image Generation on Current Noisy Quantum Computing Devices
• Order $p$ quantum Wasserstein distances from couplings
• On Quantum Circuits for Discrete Graphical Models
• Quantum locally linear embedding for nonlinear dimensionality reduction
• Quantum Inception Score
• State Classification via a Random-Walk-Based Quantum Neural Network
• QFCNN: Quantum Fourier Convolutional Neural Network
• Multidimensional Quantum Generative Modeling by Quantum Hartley Transform
• Synergic quantum generative machine learning
• Multiqubit state learning with entangling quantum generative adversarial networks
• Noise tailoring for Robust Amplitude Estimation
• Almost fault-tolerant quantum machine learning with drastic overhead reduction
• Cross-platform hardware benchmark of style-based quantum GANs for data augmentation on superconducting and trapped-ion processors
• TILT: Achieving Higher Fidelity on a Trapped-Ion Linear-Tape Quantum Computing Architecture
• Non-linear classification capability of quantum neural networks due to emergent quantum metastability
• Quantum-classical reinforcement learning for decoding noisy classical parity information
• OpticalGAN : Generative Adversarial Networks for Continuous Variable Quantum Computation
• Supervised binary classification of small-scale digit images and weighted graphs with a trapped-ion quantum processor
• Quantum circuit-like learning: A fast and scalable classical machine-learning algorithm with similar performance to quantum circuit learning
• Quantum generative modeling for financial time series with temporal correlations
• Mutual information maximizing quantum generative adversarial networks
• A Parameter-Efficient Quantum Anomaly Detection Method on a Superconducting Quantum Processor
• Adaptive Circuit Learning of Born Machine: Towards Realization of Amplitude Embedding and Quantum Data Loading
• Quantum Discriminator for Binary Classification
• Quantum transfer component analysis for domain adaptation
• ReCon: Reconfiguring Analog Rydberg Atom Quantum Computers for Quantum Generative Adversarial Networks
• Empirical Power of Quantum Encoding Methods for Binary Classification
• Quantum natural gradient with thermal-state initialization
• GAN decoder on a quantum toric code for noise-robust quantum teleportation
• Quantum Noise Sensing by generating Fake Noise
• The Holy Grail of Quantum Artificial Intelligence: Major Challenges in Accelerating the Machine Learning Pipeline
• Measuring Incompatible Observables with Quantum Neural Networks
• Finding the optimal Nash equilibrium in a discrete Rosenthal congestion game using the Quantum Alternating Operator Ansatz
• Quantum-classical simulation of quantum field theory by quantum circuit learning
• Superior resilience to poisoning and amenability to unlearning in quantum machine learning
• Quantum Machine Learning for Climate Modelling
• Towards quantum machine learning for assessing the resilience of post-quantum cryptography
• HMB-GAN: Hybrid Multi-Bézier GAN for Vector Shape Synthesis
• TabularQGAN: A quantum generative model for tabular data synthesis
• NordIQuEst: the Nordic-Estonian Quantum Computing e-Infrastructure Quest
• Quantum Algorithms for Unsupervised Machine Learning and Neural Networks
• Quantum Model-Discovery
• Quantum-assisted tracer dispersion in turbulent shear flow
• EQNN: Enhanced Quantum Neural Network
• A Quadratic Speedup in Finding Nash Equilibria of Quantum Zero-Sum Games
• Variational Quantum Generative Modeling by Sampling Expectation Values of Tunable Observables
• Quantum frequency resampling
• Quantum Spike Neural Network
• Expressive equivalence of classical and quantum restricted Boltzmann machines
• Quantum Chebyshev Probabilistic Models for Fragmentation Functions