Data re-uploading for a universal quantum classifier

Abstract

A single qubit provides sufficient computational capabilities to construct a universal quantum classifier when assisted with a classical subroutine. This fact may be surprising since a single qubit only offers a simple superposition of two states and single-qubit gates only make a rotation in the Bloch sphere. The key ingredient to circumvent these limitations is to allow for multiple data re-uploading. A quantum circuit can then be organized as a series of data re-uploading and single-qubit processing units. Furthermore, both data re-uploading and measurements can accommodate multiple dimensions in the input and several categories in the output, to conform to a universal quantum classifier. The extension of this idea to several qubits enhances the efficiency of the strategy as entanglement expands the superpositions carried along with the classification. Extensive benchmarking on different examples of the single- and multi-qubit quantum classifier validates its ability to describe and classify complex data.

arXiv comment19 pages, 9 figures

References in corpus (10)

• Quantum Machine Learning
• Supervised learning with quantum enhanced feature spaces
• Quantum support vector machine for big data classification
• Quantum machine learning in feature Hilbert spaces
• Quantum Circuit Learning
• Quantum random access memory
• The quest for a Quantum Neural Network
• Quantum Data Fitting
• Quantum generalisation of feedforward neural networks
• Unitary quantum perceptron as efficient universal approximator

Cited by in corpus (193)

• Variational Quantum Algorithms
• Noisy intermediate-scale quantum (NISQ) algorithms
• The effect of data encoding on the expressive power of variational quantum machine learning models
• Hybrid quantum-classical algorithms and quantum error mitigation
• Generalization in quantum machine learning from few training data
• Robust data encodings for quantum classifiers
• Is quantum advantage the right goal for quantum machine learning?
• Quantum machine learning beyond kernel methods
• 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
• Exploiting symmetry in variational quantum machine learning
• Generalization in Quantum Machine Learning: a Quantum Information Perspective
• Quantum Machine Learning for Chemistry and Physics
• Training Quantum Embedding Kernels on Near-Term Quantum Computers
• Qibo: a framework for quantum simulation with hardware acceleration
• Quantum computing models for artificial neural networks
• Hybrid quantum neural network for drug response prediction
• Experimental quantum adversarial learning with programmable superconducting qubits
• Quantum Machine Learning: from physics to software engineering
• A comprehensive review of Quantum Machine Learning: from NISQ to Fault Tolerance
• Quantum Methods for Neural Networks and Application to Medical Image Classification
• Theoretical Guarantees for Permutation-Equivariant Quantum Neural Networks
• Universal Approximation Property of Quantum Machine Learning Models in Quantum-Enhanced Feature Spaces
• The Meta-Variational Quantum Eigensolver (Meta-VQE): Learning energy profiles of parameterized Hamiltonians for quantum simulation
• Understanding quantum machine learning also requires rethinking generalization
• A Feasible Approach for Automatically Differentiable Unitary Coupled-Cluster on Quantum Computers
• One qubit as a Universal Approximant
• On the practical usefulness of the Hardware Efficient Ansatz
• Perceval: A Software Platform for Discrete Variable Photonic Quantum Computing
• Scaling of variational quantum circuit depth for condensed matter systems
• Machine Learning for Anomaly Detection in Particle Physics
• Quantum machine learning of large datasets using randomized measurements
• Characterizing the loss landscape of variational quantum circuits
• Generalization despite overfitting in quantum machine learning models
• Determining the proton content with a quantum computer
• Classical surrogates for quantum learning models
• Quantum unary approach to option pricing
• Variational inference with a quantum computer
• Quantum Kernel Methods for Solving Differential Equations
• Quantum Machine Learning for Finance
• Avoiding Barren Plateaus with Classical Deep Neural Networks
• Style-based quantum generative adversarial networks for Monte Carlo events
• Hybrid quantum ResNet for car classification and its hyperparameter optimization
• Quantum Machine Learning in Drug Discovery: Applications in Academia and Pharmaceutical Industries
• Natural Evolutionary Strategies for Variational Quantum Computation
• Quantum anomaly detection in the latent space of proton collision events at the LHC
• Quantum autoencoders with enhanced data encoding
• Higgs analysis with quantum classifiers
• Variational Quantum Anomaly Detection: Unsupervised mapping of phase diagrams on a physical quantum computer
• Overfitting in quantum machine learning and entangling dropout
• Quantum Transfer Learning for Real-World, Small, and High-Dimensional Datasets
• Predicting toxicity by quantum machine learning
• Quantum utility -- definition and assessment of a practical quantum advantage
• Exponential data encoding for quantum supervised learning
• Quantum Deep Hedging
• Quantum Deep Reinforcement Learning for Robot Navigation Tasks
• Learning quantum states and unitaries of bounded gate complexity
• Fock State-enhanced Expressivity of Quantum Machine Learning Models
• Multidimensional Fourier series with quantum circuits
• Uncovering Instabilities in Variational-Quantum Deep Q-Networks
• Quantum Phase Processing and its Applications in Estimating Phase and Entropies
• Entanglement entropy production in Quantum Neural Networks
• Quantum reservoir computing in finite dimensions
• Single-qubit universal classifier implemented on an ion-trap quantum device
• A performance characterization of quantum generative models
• Quantum kernels to learn the phases of quantum matter
• Noise robustness and experimental demonstration of a quantum generative adversarial network for continuous distributions
• How quantum computing can enhance biomarker discovery
• A preprocessing perspective for quantum machine learning classification advantage using NISQ algorithms
• Reduction of finite sampling noise in quantum neural networks
• Let Quantum Neural Networks Choose Their Own Frequencies
• Evolutionary Quantum Architecture Search for Parametrized Quantum Circuits
• Quantum neural networks force fields generation
• Generalization of Quantum Machine Learning Models Using Quantum Fisher Information Metric
• A duplication-free quantum neural network for universal approximation
• Classical Splitting of Parametrized Quantum Circuits
• Dequantizing quantum machine learning models using tensor networks
• A General Approach to Dropout in Quantum Neural Networks
• Data re-uploading with a single qudit
• Training robust and generalizable quantum models
• Quantum neural networks form Gaussian processes
• On the expressivity of embedding quantum kernels
• An exponentially-growing family of universal quantum circuits
• Efficient algorithms for quantum information bottleneck
• An open-source modular framework for quantum computing
• Qibolab: an open-source hybrid quantum operating system
• Quantum Vision Transformers for Quark-Gluon Classification
• VQC-Based Reinforcement Learning with Data Re-uploading: Performance and Trainability
• Incremental Data-Uploading for Full-Quantum Classification
• How to enhance quantum generative adversarial learning of noisy information
• Neural quantum kernels: training quantum kernels with quantum neural networks
• Quantum kernels with squeezed-state encoding for machine learning
• Evolution strategies: Application in hybrid quantum-classical neural networks
• Quantum computing through the lens of control: A tutorial introduction
• A quantum active learning algorithm for sampling against adversarial attacks
• Hyperparameter Importance of Quantum Neural Networks Across Small Datasets
• Hybrid quantum learning with data re-uploading on a small-scale superconducting quantum simulator
• Demonstration of a bosonic quantum classifier with data re-uploading
• Expressivity of Variational Quantum Machine Learning on the Boolean Cube
• Opportunities and challenges of quantum computing for climate modelling
• Constrained and Vanishing Expressivity of Quantum Fourier Models
• Entanglement assisted training algorithm for supervised quantum classifiers
• Quantum Lazy Training
• Jet Discrimination with Quantum Complete Graph Neural Network
• Quantum Computing for Software Engineering: Prospects
• Quantum Fourier Iterative Amplitude Estimation
• Adiabatic quantum algorithm for artificial graphene
• A Multi-Class SWAP-Test Classifier
• Symmetry-invariant quantum machine learning force fields
• Guided-SPSA: Simultaneous Perturbation Stochastic Approximation assisted by the Parameter Shift Rule
• Qudit Machine Learning
• Satellite image classification with neural quantum kernels
• The Power of One Clean Qubit in Supervised Machine Learning
• Quantum data encoding as a distinct abstraction layer in the design of quantum circuits
• Density Matrix Emulation of Quantum Recurrent Neural Networks for Multivariate Time Series Prediction
• Loop Feynman integration on a quantum computer
• Guided Quantum Compression for High Dimensional Data Classification
• Virtual distillation with noise dilution
• Multi-variable integration with a variational quantum circuit
• A didactic approach to quantum machine learning with a single qubit
• Image Classification with Rotation-Invariant Variational Quantum Circuits
• Quantum Hamiltonian Embedding of Images for Data Reuploading Classifiers
• Hybrid Quantum-Classical Autoencoders for End-to-End Radio Communication
• Photonic quantum generative adversarial networks for classical data
• Hype or Heuristic? Quantum Reinforcement Learning for Join Order Optimisation
• Quantum continual learning of quantum data realizing knowledge backward transfer
• Expressive Quantum Supervised Machine Learning using Kerr-nonlinear Parametric Oscillators
• Quantum Natural Policy Gradients: Towards Sample-Efficient Reinforcement Learning
• Photovoltaic power forecasting using quantum machine learning
• Quantum Supervised Learning
• Continuous-variable quantum kernel method on a programmable photonic quantum processor
• Variational Quantum Non-Orthogonal Optimization
• Quantum kernel learning Model constructed with small data
• On Optimizing Hyperparameters for Quantum Neural Networks
• Gradients and frequency profiles of quantum re-uploading models
• A Study on Quantum Graph Neural Networks Applied to Molecular Physics
• Maximising Quantum-Computing Expressive Power through Randomised Circuits
• ${\mathbb{Z}}_2\times {\mathbb{Z}}_2$ Equivariant Quantum Neural Networks: Benchmarking against Classical Neural Networks
• Quantum Autoencoder for Multivariate Time Series Anomaly Detection
• Universal Approximation Theorem and error bounds for quantum neural networks and quantum reservoirs
• Quantum Machine Learning Playground
• Quantum Extremal Learning
• Quantum integration of decay rates at second order in perturbation theory
• Encoding-dependent generalization bounds for parametrized quantum circuits
• Restricting to the chip architecture maintains the quantum neural network accuracy
• BCQQ: Batch-Constraint Quantum Q-Learning with Cyclic Data Re-uploading
• Quantum neural networks with multi-qubit potentials
• Supervised Learning Guarantee for Quantum AdaBoost
• Ground state-based quantum feature maps
• Quantum machine learning for multiclass classification beyond kernel methods
• Quantum-inspired clustering with light
• Hacking Cryptographic Protocols with Advanced Variational Quantum Attacks
• Learning Fourier series with parametrized quantum circuits
• Approximation and Generalization Capacities of Parametrized Quantum Circuits for Functions in Sobolev Spaces
• Quantum Neural Networks in Practice: A Comparative Study with Classical Models from Standard Data Sets to Industrial Images
• Pitfalls when tackling the exponential concentration of parameterized quantum models
• Optimized numerical gradient and Hessian estimation for variational quantum algorithms
• A Unified Framework for Quantum Supervised Learning
• Parameterized quantum comb and simpler circuits for reversing unknown qubit-unitary operations
• Quantum-Classical Autoencoder Architectures for End-to-End Radio Communication
• Quantum Active Learning
• Benchmarking Quantum Convolutional Neural Networks for Signal Classification in Simulated Gamma-Ray Burst Detection
• Typical Machine Learning Datasets as Low-Depth Quantum Circuits
• Towards Improved Quantum Machine Learning for Molecular Force Fields
• Quantum Physics-Informed Neural Networks for Maxwell's Equations: Circuit Design, "Black Hole" Barren Plateaus Mitigation, and GPU Acceleration
• High-Accuracy Temporal Prediction via Experimental Quantum Reservoir Computing in Correlated Spins
• Universal approximation of continuous functions with minimal quantum circuits
• Demonstration of sequential processors with quantum advantage and analysis of classical performance limits
• Building Continuous Quantum-Classical Bayesian Neural Networks for a Classical Clinical Dataset
• Dissipative realization of a quantum distance-based classifier using open quantum walks
• Shot-based quantum encoding: a data-loading paradigm for quantum neural networks
• Robustness of optimized numerical estimation schemes for noisy variational quantum algorithms
• Quantum neural network autoencoder and classifier applied to an industrial case study
• Qiskit-Torch-Module: Fast Prototyping of Quantum Neural Networks
• Guided Graph Compression for Quantum Graph Neural Networks
• Single-Qudit Quantum Neural Networks for Multiclass Classification
• A genetic algorithm to generate maximally orthogonal frames in complex space
• A variational quantum algorithm for entanglement quantification
• Double descent in quantum kernel methods
• Interpolation-based coordinate descent method for parameterized quantum circuits
• Quantum-Enhanced Neural Exchange-Correlation Functionals
• Detecting underdetermination in parameterized quantum circuits
• HMB-GAN: Hybrid Multi-Bézier GAN for Vector Shape Synthesis
• Learning complexity gradually in quantum machine learning models
• Extended parameter shift rules with minimal derivative variance for parameterized quantum circuits
• Single Qubit Multi-Party Transmission Using Universal Symmetric Quantum Cloning
• Noise-Resilient Quantum Reinforcement Learning
• Hybrid quantum recurrent neural network for remaining useful life prediction of turbofan engines
• Superior resilience to poisoning and amenability to unlearning in quantum machine learning
• Quantum feature-map learning with reduced resource overhead
• QMC-Net: Data-Aware Quantum Representations for Remote Sensing Image Classification
• QAISim: A Toolkit for Modeling and Simulation of AI in Quantum Cloud Computing Environments
• Quantum Machine Learning for Climate Modelling