Robust data encodings for quantum classifiers

Abstract

Data representation is crucial for the success of machine learning models. In the context of quantum machine learning with near-term quantum computers, equally important considerations of how to efficiently input (encode) data and effectively deal with noise arise. In this work, we study data encodings for binary quantum classification and investigate their properties both with and without noise. For the common classifier we consider, we show that encodings determine the classes of learnable decision boundaries as well as the set of points which retain the same classification in the presence of noise. After defining the notion of a robust data encoding, we prove several results on robustness for different channels, discuss the existence of robust encodings, and prove an upper bound on the number of robust points in terms of fidelities between noisy and noiseless states. Numerical results for several example implementations are provided to reinforce our findings.

18 pages, 10 figures

References in corpus (52)

• Scikit-learn: Machine Learning in Python
• Quantum Computing in the NISQ era and beyond
• Supplementary information for "Quantum supremacy using a programmable superconducting processor"
• Polynomial-Time Algorithms for Prime Factorization and Discrete Logarithms on a Quantum Computer
• A variational eigenvalue solver on a quantum processor
• Quantum algorithm for solving linear systems of equations
• Supervised learning with quantum enhanced feature spaces
• Barren plateaus in quantum neural network training landscapes
• The theory of variational hybrid quantum-classical algorithms
• Decoherence Free Subspaces for Quantum Computation
• A Quantum Approximate Optimization Algorithm
• Dynamical Decoupling of Open Quantum Systems
• Quantum machine learning in feature Hilbert spaces
• Quantum Convolutional Neural Networks
• Error mitigation for short-depth quantum circuits
• Parameterized quantum circuits as machine learning models
• Circuit-centric quantum classifiers
• Scalable Quantum Simulation of Molecular Energies
• Data re-uploading for a universal quantum classifier
• Quantum generative adversarial networks
• Quantum-Classical Computation of Schwinger Model Dynamics using Quantum Computers
• Transfer learning in hybrid classical-quantum neural networks
• An initialization strategy for addressing barren plateaus in parametrized quantum circuits
• A generative modeling approach for benchmarking and training shallow quantum circuits
• Quantum-assisted quantum compiling
• Hierarchical quantum classifiers
• The Expressive Power of Parameterized Quantum Circuits
• Differentiable Learning of Quantum Circuit Born Machine
• A universal quantum circuit for two-qubit transformations with three CNOT gates
• QuEST and High Performance Simulation of Quantum Computers
• Variational Quantum State Diagonalization
• Tapering off qubits to simulate fermionic Hamiltonians
• Noise Resilience of Variational Quantum Compiling
• Variational algorithms for linear algebra
• Digitization of Scalar Fields for Quantum Computing
• The Born Supremacy: Quantum Advantage and Training of an Ising Born Machine
• Quantum Adversarial Machine Learning
• Overview and Comparison of Gate Level Quantum Software Platforms
• Decoding quantum errors with subspace expansions
• A quantum algorithm to train neural networks using low-depth circuits
• Quantum embeddings for machine learning
• Variational Consistent Histories as a Hybrid Algorithm for Quantum Foundations
• Near-term quantum algorithms for linear systems of equations
• Quantum linear systems algorithms: a primer
• Characterizing local noise in QAOA circuits
• Quantum classification of the MNIST dataset with Slow Feature Analysis
• Analysis and synthesis of feature map for kernel-based quantum classifier
• Noise-Resilient Variational Hybrid Quantum-Classical Optimization
• Analysis of Quantum Approximate Optimization Algorithm under Realistic Noise in Superconducting Qubits
• Cost function embedding and dataset encoding for machine learning with parameterized quantum circuits
• Quantum statistical query learning
• Quantum Mean Embedding of Probability Distributions

Cited by in corpus (97)

• The effect of data encoding on the expressive power of variational quantum machine learning models
• Power of data in quantum machine learning
• Challenges and Opportunities in Quantum Machine Learning
• Quantum convolutional neural network for classical data classification
• The Bitter Truth About Quantum Algorithms in the NISQ Era
• Quantum noise protects quantum classifiers against adversaries
• Efficient measure for the expressivity of variational quantum algorithms
• Quantum computing models for artificial neural networks
• Anomaly detection in high-energy physics using a quantum autoencoder
• Quantum Machine Learning for Particle Physics using a Variational Quantum Classifier
• Quantum Machine Learning: from physics to software engineering
• Recent advances for quantum classifiers
• A comprehensive review of Quantum Machine Learning: from NISQ to Fault Tolerance
• Biology and medicine in the landscape of quantum advantages
• Universal Approximation Property of Quantum Machine Learning Models in Quantum-Enhanced Feature Spaces
• Towards quantum enhanced adversarial robustness in machine learning
• Subtleties in the trainability of quantum machine learning models
• Classification with Quantum Machine Learning: A Survey
• Benchmarking Adversarially Robust Quantum Machine Learning at Scale
• Classical-to-quantum convolutional neural network transfer learning
• Analysis and synthesis of feature map for kernel-based quantum classifier
• Reflection Equivariant Quantum Neural Networks for Enhanced Image Classification
• Variational inference with a quantum computer
• Avoiding Barren Plateaus with Classical Deep Neural Networks
• Robust in Practice: Adversarial Attacks on Quantum Machine Learning
• Quantum Machine Learning in Drug Discovery: Applications in Academia and Pharmaceutical Industries
• Quantum anomaly detection in the latent space of proton collision events at the LHC
• ResQNets: A Residual Approach for Mitigating Barren Plateaus in Quantum Neural Networks
• Optimal Provable Robustness of Quantum Classification via Quantum Hypothesis Testing
• Quantum autoencoders with enhanced data encoding
• Practical Quantum K-Means Clustering: Performance Analysis and Applications in Energy Grid Classification
• Predicting toxicity by quantum machine learning
• Tree tensor network classifiers for machine learning: from quantum-inspired to quantum-assisted
• Quantum Deep Reinforcement Learning for Robot Navigation Tasks
• Generative machine learning with tensor networks: benchmarks on near-term quantum computers
• Entangled Datasets for Quantum Machine Learning
• Quantum kernels to learn the phases of quantum matter
• Drastic Circuit Depth Reductions with Preserved Adversarial Robustness by Approximate Encoding for Quantum Machine Learning
• Let Quantum Neural Networks Choose Their Own Frequencies
• Evolutionary Quantum Architecture Search for Parametrized Quantum Circuits
• Calibrating the role of entanglement in variational quantum circuits
• Quantum Transfer Learning with Adversarial Robustness for Classification of High-Resolution Image Datasets
• Harnessing Quantum Extreme Learning Machines for image classification
• Training robust and generalizable quantum models
• HamLib: A library of Hamiltonians for benchmarking quantum algorithms and hardware
• Neural Quantum Embedding: Pushing the Limits of Quantum Supervised Learning
• Networked Quantum Services
• The quantum cost function concentration dependency on the parametrization expressivity
• The Unified Effect of Data Encoding, Ansatz Expressibility and Entanglement on the Trainability of HQNNs
• Ensemble-learning error mitigation for variational quantum shallow-circuit classifiers
• Fitting a Collider in a Quantum Computer: Tackling the Challenges of Quantum Machine Learning for Big Datasets
• Incremental Data-Uploading for Full-Quantum Classification
• Variational Quantum Cloning: Improving Practicality for Quantum Cryptanalysis
• On exploring the potential of quantum auto-encoder for learning quantum systems
• Variational quantum state discriminator for supervised machine learning
• Evolution strategies: Application in hybrid quantum-classical neural networks
• Solving The Vehicle Routing Problem via Quantum Support Vector Machines
• Decohering Tensor Network Quantum Machine Learning Models
• Kernel-based quantum regressor models learn non-Markovianity
• Quantum support vector data description for anomaly detection
• A Continuous Variable Born Machine
• Quantum and Quantum-Inspired Stereographic K Nearest-Neighbour Clustering
• Investigating the Effect of Noise on the Training Performance of Hybrid Quantum Neural Networks
• F-Divergences and Cost Function Locality in Generative Modelling with Quantum Circuits
• Qudit Machine Learning
• Quantum data encoding as a distinct abstraction layer in the design of quantum circuits
• SEQUENT: Towards Traceable Quantum Machine Learning using Sequential Quantum Enhanced Training
• Qsun: an open-source platform towards practical quantum machine learning applications
• Quantum Information Masking in Non-Hermitian Systems and Robustness
• Image Classification with Rotation-Invariant Variational Quantum Circuits
• Hybrid Quantum Machine Learning Assisted Classification of COVID-19 from Computed Tomography Scans
• Adversarial Robustness Guarantees for Quantum Classifiers
• The dilemma of quantum neural networks
• QuanTest: Entanglement-Guided Testing of Quantum Neural Network Systems
• Generating Universal Adversarial Perturbations for Quantum Classifiers
• Quantum Support Vector Machines for Continuum Suppression in B Meson Decays
• On Classifying Images using Quantum Image Representation
• QDCNN: Quantum Dilated Convolutional Neural Network
• An example of use of Variational Methods in Quantum Machine Learning
• Precise Image Generation on Current Noisy Quantum Computing Devices
• Non-parametric Semi-Supervised Learning in Many-body Hilbert Space with Rescaled Logarithmic Fidelity
• Learning Equivariant Maps with Variational Quantum Circuits
• ResQuNNs: Towards Enabling Deep Learning in Quantum Convolution Neural Networks
• Quanvolutional Neural Networks for Pneumonia Detection: An Efficient Quantum-Assisted Feature Extraction Paradigm
• Optimal Qubit Mapping Search for Encoding Classical Data into Matrix Product State Representation with Minimal Loss
• Hybrid Quantum Classical Graph Neural Networks for Particle Track Reconstruction
• Quadratic speed-ups in quantum kernelized binary classification
• Experimentally validated quantum-secure federated learning over a multi-user quantum network
• Policy Gradients using Variational Quantum Circuits
• Accelerating variational quantum algorithms with multiple quantum processors
• Efficient Sparse State Preparation via Quantum Walks
• Quantum neural network autoencoder and classifier applied to an industrial case study
• Quantum natural gradient with thermal-state initialization
• Data-driven Quantum Dynamical Embedding Method for Long-term Prediction on Near-term Quantum Computers
• Quantifying the Expressive Capacity of Quantum Systems: Fundamental Limits and Eigentasks
• Schmidt quantum compressor
• Noise-resilient and resource-efficient hybrid algorithm for robust quantum gap estimation