Automatic design of quantum feature maps

Abstract

We propose a new technique for the automatic generation of optimal ad-hoc ansätze for classification by using quantum support vector machine (QSVM). This efficient method is based on NSGA-II multiobjective genetic algorithms which allow both maximize the accuracy and minimize the ansatz size. It is demonstrated the validity of the technique by a practical example with a non-linear dataset, interpreting the resulting circuit and its outputs. We also show other application fields of the technique that reinforce the validity of the method, and a comparison with classical classifiers in order to understand the advantages of using quantum machine learning.

References in corpus (26)

• Quantum Machine Learning
• Supervised learning with quantum enhanced feature spaces
• Barren plateaus in quantum neural network training landscapes
• Quantum support vector machine for big data classification
• Quantum machine learning in feature Hilbert spaces
• Quantum principal component analysis
• Parameterized quantum circuits as machine learning models
• Expressibility and entangling capability of parameterized quantum circuits for hybrid quantum-classical algorithms
• Exploiting Nonlinear Recurrence and Fractal Scaling Properties for Voice Disorder Detection
• Quantum generative adversarial learning
• Quantum generative adversarial networks
• Quantum autoencoders for efficient compression of quantum data
• An initialization strategy for addressing barren plateaus in parametrized quantum circuits
• The Expressive Power of Parameterized Quantum Circuits
• Structure optimization for parameterized quantum circuits
• Quantum machine learning for quantum anomaly detection
• Quantum Discriminant Analysis for Dimensionality Reduction and Classification
• q-means: A quantum algorithm for unsupervised machine learning
• One qubit as a Universal Approximant
• Quantum autoencoders via quantum adders with genetic algorithms
• Adaptive pruning-based optimization of parameterized quantum circuits
• Quantum algorithm and quantum circuit for A-Optimal Projection: dimensionality reduction
• Approximate Quantum Adders with Genetic Algorithms: An IBM Quantum Experience
• MoG-VQE: Multiobjective genetic variational quantum eigensolver
• Natural Evolutionary Strategies for Variational Quantum Computation
• Natural evolution strategies and variational Monte Carlo

Cited by in corpus (20)

• Robust resource-efficient quantum variational ansatz through evolutionary algorithm
• Quantum Kernel Methods under Scrutiny: A Benchmarking Study
• Quantum anomaly detection in the latent space of proton collision events at the LHC
• Quantum Architecture Search: A Survey
• AutoQML: Automatic Generation and Training of Robust Quantum-Inspired Classifiers by Using Genetic Algorithms on Grayscale Images
• A preprocessing perspective for quantum machine learning classification advantage using NISQ algorithms
• Quantum AI simulator using a hybrid CPU-FPGA approach
• Distributed quantum architecture search
• On the expressivity of embedding quantum kernels
• Quantum Advantage Seeker with Kernels (QuASK): a software framework to speed up the research in quantum machine learning
• Reinforcement learning-based architecture search for quantum machine learning
• Exploring the optimality of approximate state preparation quantum circuits with a genetic algorithm
• Hybrid Genetic Optimisation for Quantum Feature Map Design
• Random coordinate descent: a simple alternative for optimizing parameterized quantum circuits
• Enhanced feature encoding and classification on distributed quantum hardware
• Learning the expressibility of quantum circuit ansatz using transformer
• On the similarity of bandwidth-tuned quantum kernels and classical kernels
• Benchmarking of quantum fidelity kernels for Gaussian process regression
• Quantum feature-map learning with reduced resource overhead
• Quantum generative classification with mixed states