A comprehensive review of Quantum Machine Learning: from NISQ to Fault Tolerance

Abstract

Quantum machine learning, which involves running machine learning algorithms on quantum devices, has garnered significant attention in both academic and business circles. In this paper, we offer a comprehensive and unbiased review of the various concepts that have emerged in the field of quantum machine learning. This includes techniques used in Noisy Intermediate-Scale Quantum (NISQ) technologies and approaches for algorithms compatible with fault-tolerant quantum computing hardware. Our review covers fundamental concepts, algorithms, and the statistical learning theory pertinent to quantum machine learning.

28 pages. Invited review

References in corpus (36)

• Quantum algorithm for solving linear systems of equations
• A Quantum Approximate Optimization Algorithm
• Quantum computing with trapped ions
• Challenges and Opportunities in Quantum Machine Learning
• Quantum advantage in learning from experiments
• Hybrid quantum-classical algorithms and quantum error mitigation
• Propagating phonons coupled to an artificial atom
• The randomized measurement toolbox
• Non-convex Optimization for Machine Learning
• Chaos, Complexity, and Random Matrices
• Provably efficient machine learning for quantum many-body problems
• Quantum machine learning beyond kernel methods
• Robust Online Hamiltonian Learning
• Efficient estimation of Pauli observables by derandomization
• Theory of overparametrization in quantum neural networks
• Equivalence of quantum barren plateaus to cost concentration and narrow gorges
• Towards understanding the power of quantum kernels in the NISQ era
• Towards provably efficient quantum algorithms for large-scale machine-learning models
• Barren plateaus in quantum tensor network optimization
• Representation Learning via Quantum Neural Tangent Kernels
• Reinforcement Learning assisted Quantum Optimization
• Tight bounds on the convergence of noisy random circuits to the uniform distribution
• Natural Evolutionary Strategies for Variational Quantum Computation
• Quantum Bootstrapping via Compressed Quantum Hamiltonian Learning
• Improved machine learning algorithm for predicting ground state properties
• Classical shadows with Pauli-invariant unitary ensembles
• Learning Unitaries by Gradient Descent
• A semi-agnostic ansatz with variable structure for quantum machine learning
• Step-by-Step HHL Algorithm Walkthrough to Enhance the Understanding of Critical Quantum Computing Concepts
• Effects of quantum resources on the statistical complexity of quantum circuits
• Quantum Observables for continuous control of the Quantum Approximate Optimization Algorithm via Reinforcement Learning
• The battle of clean and dirty qubits in the era of partial error correction
• Quantifying fermionic nonlinearity of quantum circuits
• Fundamental causal bounds of quantum random access memories
• An Introduction to Error-Correcting Codes: From Classical to Quantum
• Predicting Ground State Properties: Constant Sample Complexity and Deep Learning Algorithms

Cited by in corpus (18)

• Quantum Machine Learning for Digital Health? A Systematic Review
• Simulating fluid flows with quantum computing
• Image Classification with Rotation-Invariant Variational Quantum Circuits
• Quantum Supervised Learning
• Impact of Amplitude and Phase Damping Noise on Quantum Reinforcement Learning: Challenges and Opportunities
• Engineering tunable decoherence-free subspaces with collective atom-cavity interactions
• Data-Dependent Generalization Bounds for Parameterized Quantum Models Under Noise
• Quantum memristor with vacuum--one-photon qubits
• Property-guided Inverse Design of Metal-Organic Frameworks Using Quantum Natural Language Processing
• Digital-Analog Quantum Machine Learning
• Accelerating Quantum Eigensolver Algorithms With Machine Learning
• Noise tolerance via reinforcement: Learning a reinforced quantum dynamics
• Single-Qudit Quantum Neural Networks for Multiclass Classification
• Subsampling Factorization Machine Annealing
• TabularQGAN: A quantum generative model for tabular data synthesis
• Moments of Quantum Channel Ensembles
• Superior resilience to poisoning and amenability to unlearning in quantum machine learning
• Compositional Quantum Control Flow with Efficient Compilation in Qunity