Recent advances for quantum classifiers

Abstract

Machine learning has achieved dramatic success in a broad spectrum of applications. Its interplay with quantum physics may lead to unprecedented perspectives for both fundamental research and commercial applications, giving rise to an emergent research frontier of quantum machine learning. Along this line, quantum classifiers, which are quantum devices that aim to solve classification problems in machine learning, have attracted tremendous attention recently. In this review, we give a relatively comprehensive overview for the studies of quantum classifiers, with a focus on recent advances. First, we will review a number of quantum classification algorithms, including quantum support vector machines, quantum kernel methods, quantum decision tree classifiers, quantum nearest neighbor algorithms, and quantum annealing based classifiers. Then, we move on to introduce the variational quantum classifiers, which are essentially variational quantum circuits for classifications. We will review different architectures for constructing variational quantum classifiers and introduce the barren plateau problem, where the training of quantum classifiers might be hindered by the exponentially vanishing gradient. In addition, the vulnerability aspect of quantum classifiers in the setting of adversarial learning and the recent experimental progress on different quantum classifiers will also be discussed.

invited review, 24 pages, 11 figures

References in corpus (36)

• Supplementary information for "Quantum supremacy using a programmable superconducting processor"
• Quantum algorithm for solving linear systems of equations
• Quantum computational advantage using photons
• Recurrent Neural Network Regularization
• ZOO: Zeroth Order Optimization based Black-box Attacks to Deep Neural Networks without Training Substitute Models
• Strong quantum computational advantage using a superconducting quantum processor
• Quantum random access memory
• A class of quantum many-body states that can be efficiently simulated
• Quantum-enhanced machine learning
• Quantum convolutional neural network for classical data classification
• A Grand Unification of Quantum Algorithms
• General parameter-shift rules for quantum gradients
• Experimental Realization of Quantum Artificial Intelligence
• QuantumNAS: Noise-Adaptive Search for Robust Quantum Circuits
• Capsule Network Performance on Complex Data
• Machine learning meets quantum physics
• ScaffCC: Scalable Compilation and Analysis of Quantum Programs
• Efficient measure for the expressivity of variational quantum algorithms
• Realizing Quantum Convolutional Neural Networks on a Superconducting Quantum Processor to Recognize Quantum Phases
• Quantum federated learning through blind quantum computing
• Practical optimization for hybrid quantum-classical algorithms
• Towards understanding the power of quantum kernels in the NISQ era
• Learning to learn with quantum neural networks via classical neural networks
• Training a Binary Classifier with the Quantum Adiabatic Algorithm
• The Presence and Absence of Barren Plateaus in Tensor-network Based Machine Learning
• Generalized quantum circuit differentiation rules
• MoG-VQE: Multiobjective genetic variational quantum eigensolver
• Universal Adversarial Examples and Perturbations for Quantum Classifiers
• Image classification using quantum inference on the D-Wave 2X
• Optimal training of variational quantum algorithms without barren plateaus
• Representation of binary classification trees with binary features by quantum circuits
• Hybrid quantum-classical classifier based on tensor network and variational quantum circuit
• Quantum Continual Learning Overcoming Catastrophic Forgetting
• Encoding-dependent generalization bounds for parametrized quantum circuits
• Restricted Boltzmann Machines for galaxy morphology classification with a quantum annealer
• Quantum Generative Training Using Rényi Divergences

Cited by in corpus (9)

• Experimental quantum adversarial learning with programmable superconducting qubits
• Multiclass classification using quantum convolutional neural networks with hybrid quantum-classical learning
• Quantum kernels for real-world predictions based on electronic health records
• Quantum machine learning of large datasets using randomized measurements
• Non-IID Quantum Federated Learning with One-shot Communication Complexity
• Fock State-enhanced Expressivity of Quantum Machine Learning Models
• Quantum Capsule Networks
• A duplication-free quantum neural network for universal approximation
• Analog quantum variational embedding classifier