Training Quantum Embedding Kernels on Near-Term Quantum Computers

Abstract

Kernel methods are a cornerstone of classical machine learning. The idea of using quantum computers to compute kernels has recently attracted attention. Quantum embedding kernels (QEKs) constructed by embedding data into the Hilbert space of a quantum computer are a particular quantum kernel technique that allows to gather insights into learning problems and that are particularly suitable for noisy intermediate-scale quantum devices. In this work, we first provide an accessible introduction to quantum embedding kernels and then analyze the practical issues arising when realizing them on a noisy near-term quantum computer. We focus on quantum embedding kernels with variational parameters. These variational parameters are optimized for a given dataset by increasing the kernel-target alignment, a heuristic connected to the achievable classification accuracy. We further show under which conditions noise from device imperfections influences the predicted kernel and provide a strategy to mitigate these detrimental effects which is tailored to quantum embedding kernels. We also address the influence of finite sampling and derive bounds that put guarantees on the quality of the kernel matrix. We illustrate our findings by numerical experiments and tests on actual hardware.

arXiv comment19 pages, 13 figures

References in corpus (34)

• Supplementary information for "Quantum supremacy using a programmable superconducting processor"
• Quantum Machine Learning
• Variational Quantum Algorithms
• Supervised learning with quantum enhanced feature spaces
• Barren plateaus in quantum neural network training landscapes
• The theory of variational hybrid quantum-classical algorithms
• Noisy intermediate-scale quantum (NISQ) algorithms
• Quantum machine learning in feature Hilbert spaces
• Quantum Circuit Learning
• Quantum principal component analysis
• Error mitigation for short-depth quantum circuits
• Quantum fingerprinting
• Predicting Many Properties of a Quantum System from Very Few Measurements
• Cost Function Dependent Barren Plateaus in Shallow Parametrized Quantum Circuits
• Extending the computational reach of a noisy superconducting quantum processor
• 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
• A rigorous and robust quantum speed-up in supervised machine learning
• Practical Quantum Error Mitigation for Near-Future Applications
• Direct Fidelity Estimation from Few Pauli Measurements
• Algorithms for Learning Kernels Based on Centered Alignment
• Learning the quantum algorithm for state overlap
• Learning-based quantum error mitigation
• PennyLane: Automatic differentiation of hybrid quantum-classical computations
• Virtual Distillation for Quantum Error Mitigation
• Exponential Error Suppression for Near-Term Quantum Devices
• Quantum computing models for artificial neural networks
• On barren plateaus and cost function locality in variational quantum algorithms
• Systematic errors in current quantum state tomography tools
• Towards understanding the power of quantum kernels in the NISQ era
• Unified approach to data-driven quantum error mitigation
• Beyond the swap test: optimal estimation of quantum state overlap
• Experimental quantum kernel machine learning with nuclear spins in a solid

Cited by in corpus (43)

• Challenges and Opportunities in Quantum Machine Learning
• Understanding quantum machine learning also requires rethinking generalization
• Subtleties in the trainability of quantum machine learning models
• The complexity of quantum support vector machines
• Quantum machine learning of large datasets using randomized measurements
• Quantum Kernel Methods under Scrutiny: A Benchmarking Study
• Unravelling physics beyond the standard model with classical and quantum anomaly detection
• Quantum Phase Recognition via Quantum Kernel Methods
• Benchmarking quantum machine learning kernel training for classification tasks
• Noisy Quantum Kernel Machines
• Reduction of finite sampling noise in quantum neural networks
• Let Quantum Neural Networks Choose Their Own Frequencies
• Quantum AI simulator using a hybrid CPU-FPGA approach
• On the expressivity of embedding quantum kernels
• Neural Quantum Embedding: Pushing the Limits of Quantum Supervised Learning
• Quantum Kernel Alignment with Stochastic Gradient Descent
• On exploring the potential of quantum auto-encoder for learning quantum systems
• Neural quantum kernels: training quantum kernels with quantum neural networks
• Efficient Parameter Optimisation for Quantum Kernel Alignment: A Sub-sampling Approach in Variational Training
• A Quantum Kernel Learning Approach to Acoustic Modeling for Spoken Command Recognition
• Single-component gradient rules for variational quantum algorithms
• Pulsar Classification: Comparing Quantum Convolutional Neural Networks and Quantum Support Vector Machines
• Hybrid Genetic Optimisation for Quantum Feature Map Design
• Enhanced feature encoding and classification on distributed quantum hardware
• Quantum Kernel Learning for Small Dataset Modeling in Semiconductor Fabrication: Application to Ohmic Contact
• Quantum Kernel Machine Learning With Continuous Variables
• The Inductive Bias of Quantum Kernels
• On the similarity of bandwidth-tuned quantum kernels and classical kernels
• Experimental benchmarking of quantum state overlap estimation strategies with photonic systems
• Quantum machine learning for multiclass classification beyond kernel methods
• The Quantum Density Matrix and its many uses: From quantum structure to quantum chaos and noisy simulators
• Quantum Neural Networks in Practice: A Comparative Study with Classical Models from Standard Data Sets to Industrial Images
• QUACK: Quantum Aligned Centroid Kernel
• Predicting Open-Hole Laminates Failure Using Support Vector Machines With Classical and Quantum Kernels
• Assessing Projected Quantum Kernels for the Classification of IoT Data
• Quantum Kernel Methods: Convergence Theory, Separation Bounds and Applications to Marketing Analytics
• Quantum fidelity kernel with a trapped-ion simulation platform
• Double descent in quantum kernel methods
• Benchmarking of quantum fidelity kernels for Gaussian process regression
• Quantum Algorithms for Causal Estimands
• New perspectives on quantum kernels through the lens of entangled tensor kernels
• Equivalence between exponential concentration in quantum machine learning kernels and barren plateaus in variational algorithms
• Quantum feature-map learning with reduced resource overhead