Analysis and synthesis of feature map for kernel-based quantum classifier

Abstract

A method for analyzing the feature map for the kernel-based quantum classifier is developed; that is, we give a general formula for computing a lower bound of the exact training accuracy, which helps us to see whether the selected feature map is suitable for linearly separating the dataset. We show a proof of concept demonstration of this method for a class of 2-qubit classifier, with several 2-dimensional dataset. Also, a synthesis method, that combines different kernels to construct a better-performing feature map in a lager feature space, is presented.

arXiv comment9 pages, 10 figures, 4 tables

References in corpus (4)

• Supervised learning with quantum enhanced feature spaces
• Robust data encodings for quantum classifiers
• Physical-Layer Supervised Learning Assisted by an Entangled Sensor Network
• An All-Pair Quantum SVM Approach for Big Data Multiclass Classification

Cited by in corpus (13)

• Robust data encodings for quantum classifiers
• Solving nonlinear differential equations with differentiable quantum circuits
• Universal expressiveness of variational quantum classifiers and quantum kernels for support vector machines
• Learning temporal data with variational quantum recurrent neural network
• Application of quantum machine learning using quantum kernel algorithms on multiclass neuron M type classification
• Neural Quantum Embedding: Pushing the Limits of Quantum Supervised Learning
• The Unified Effect of Data Encoding, Ansatz Expressibility and Entanglement on the Trainability of HQNNs
• Variational quantum state discriminator for supervised machine learning
• Quantum Gaussian process model of potential energy surface for a polyatomic molecule
• Hybrid Genetic Optimisation for Quantum Feature Map Design
• Measurement-based quantum machine learning
• Quantum enhanced stratification of Breast Cancer: exploring quantum expressivity for real omics data
• Multi-channel convolutional neural quantum embedding