The power of quantum neural networks

Abstract

Fault-tolerant quantum computers offer the promise of dramatically improving machine learning through speed-ups in computation or improved model scalability. In the near-term, however, the benefits of quantum machine learning are not so clear. Understanding expressibility and trainability of quantum models-and quantum neural networks in particular-requires further investigation. In this work, we use tools from information geometry to define a notion of expressibility for quantum and classical models. The effective dimension, which depends on the Fisher information, is used to prove a novel generalisation bound and establish a robust measure of expressibility. We show that quantum neural networks are able to achieve a significantly better effective dimension than comparable classical neural networks. To then assess the trainability of quantum models, we connect the Fisher information spectrum to barren plateaus, the problem of vanishing gradients. Importantly, certain quantum neural networks can show resilience to this phenomenon and train faster than classical models due to their favourable optimisation landscapes, captured by a more evenly spread Fisher information spectrum. Our work is the first to demonstrate that well-designed quantum neural networks offer an advantage over classical neural networks through a higher effective dimension and faster training ability, which we verify on real quantum hardware.

arXiv comment25 pages, 10 figures

References in corpus (23)

• Supervised learning with quantum enhanced feature spaces
• Barren plateaus in quantum neural network training landscapes
• Quantum Convolutional Neural Networks
• Cost Function Dependent Barren Plateaus in Shallow Parametrized Quantum Circuits
• Circuit-centric quantum classifiers
• Expressibility and entangling capability of parameterized quantum circuits for hybrid quantum-classical algorithms
• Noise-Induced Barren Plateaus in Variational Quantum Algorithms
• The effect of data encoding on the expressive power of variational quantum machine learning models
• Power of data in quantum machine learning
• The quest for a Quantum Neural Network
• Connecting ansatz expressibility to gradient magnitudes and barren plateaus
• Quantum machine learning: a classical perspective
• Quantum autoencoders for efficient compression of quantum data
• Continuous-variable quantum neural networks
• Layerwise learning for quantum neural networks
• The Expressive Power of Parameterized Quantum Circuits
• Soundness and completeness of quantum root-mean-square errors
• Stochastic gradient descent for hybrid quantum-classical optimization
• Large gradients via correlation in random parameterized quantum circuits
• Higher Order Derivatives of Quantum Neural Networks with Barren Plateaus
• Expressibility of the alternating layered ansatz for quantum computation
• Learning to learn with quantum neural networks via classical neural networks
• Characterizing the loss landscape of variational quantum circuits

Cited by in corpus (111)

• Variational Quantum Algorithms
• Noisy intermediate-scale quantum (NISQ) algorithms
• The Variational Quantum Eigensolver: a review of methods and best practices
• Noise-Induced Barren Plateaus in Variational Quantum Algorithms
• Connecting ansatz expressibility to gradient magnitudes and barren plateaus
• Generalization in quantum machine learning from few training data
• Absence of Barren Plateaus in Quantum Convolutional Neural Networks
• Effect of barren plateaus on gradient-free optimization
• Is quantum advantage the right goal for quantum machine learning?
• QuantumNAS: Noise-Adaptive Search for Robust Quantum Circuits
• Trainability of Dissipative Perceptron-Based Quantum Neural Networks
• Theory of overparametrization in quantum neural networks
• Generalization in Quantum Machine Learning: a Quantum Information Perspective
• Quantum Machine Learning for Chemistry and Physics
• Quantum annealing initialization of the quantum approximate optimization algorithm
• Equivalence of quantum barren plateaus to cost concentration and narrow gorges
• Capacity and quantum geometry of parametrized quantum circuits
• Qubit-excitation-based adaptive variational quantum eigensolver
• Higher Order Derivatives of Quantum Neural Networks with Barren Plateaus
• Efficient measure for the expressivity of variational quantum algorithms
• Fisher Information in Noisy Intermediate-Scale Quantum Applications
• Quantum computing models for artificial neural networks
• Mixed Quantum-Classical Method For Fraud Detection with Quantum Feature Selection
• QNLP in Practice: Running Compositional Models of Meaning on a Quantum Computer
• Recent advances for quantum classifiers
• Quantum Computing for Molecular Biology
• Theoretical Guarantees for Permutation-Equivariant Quantum Neural Networks
• Biology and medicine in the landscape of quantum advantages
• Layer VQE: A Variational Approach for Combinatorial Optimization on Noisy Quantum Computers
• Multiclass classification using quantum convolutional neural networks with hybrid quantum-classical learning
• Representation Learning via Quantum Neural Tangent Kernels
• Out-of-distribution generalization for learning quantum dynamics
• Subtleties in the trainability of quantum machine learning models
• Variational Quantum Eigensolver with Reduced Circuit Complexity
• The complexity of quantum support vector machines
• Analytic theory for the dynamics of wide quantum neural networks
• Generalization despite overfitting in quantum machine learning models
• Graph neural network initialisation of quantum approximate optimisation
• Quantum phase detection generalisation from marginal quantum neural network models
• Variational inference with a quantum computer
• Deep quantum neural networks equipped with backpropagation on a superconducting processor
• Quantum Kernel Methods for Solving Differential Equations
• Quantum Machine Learning for Finance
• Benchmarking simulated and physical quantum processing units using quantum and hybrid algorithms
• Hybrid quantum ResNet for car classification and its hyperparameter optimization
• Quantum pixel representations and compression for $N$-dimensional images
• Quantum Phase Recognition via Quantum Kernel Methods
• Variational quantum process tomography
• Medical image classification via quantum neural networks
• Quantum Transfer Learning for Real-World, Small, and High-Dimensional Datasets
• Variational Quantum Classifiers Through the Lens of the Hessian
• Dynamical simulation via quantum machine learning with provable generalization
• Classical versus Quantum: comparing Tensor Network-based Quantum Circuits on LHC data
• Structural risk minimization for quantum linear classifiers
• A semi-agnostic ansatz with variable structure for quantum machine learning
• Quantum reservoir computation utilising scale-free networks
• AutoQML: Automatic Generation and Training of Robust Quantum-Inspired Classifiers by Using Genetic Algorithms on Grayscale Images
• Neural network-based prediction of the secret-key rate of quantum key distribution
• Fock State-enhanced Expressivity of Quantum Machine Learning Models
• Entanglement entropy production in Quantum Neural Networks
• Quantum machine learning with adaptive linear optics
• Entangled Datasets for Quantum Machine Learning
• Variational quantum one-class classifier
• Hierarchical quantum circuit representations for neural architecture search
• Noisy Quantum Kernel Machines
• Learning Quantum Processes and Hamiltonians via the Pauli Transfer Matrix
• Evaluation of Parameterized Quantum Circuits with Cross-Resonance Pulse-Driven Entanglers
• Quantum neural networks force fields generation
• The Quantum Path Kernel: a Generalized Quantum Neural Tangent Kernel for Deep Quantum Machine Learning
• Quantum Mathematics in Artificial Intelligence
• Numerical evidence against advantage with quantum fidelity kernels on classical data
• Pulse-efficient quantum machine learning
• Rapid training of quantum recurrent neural networks
• An exponentially-growing family of universal quantum circuits
• Quantum Quantile Mechanics: Solving Stochastic Differential Equations for Generating Time-Series
• Quantum Advantage Seeker with Kernels (QuASK): a software framework to speed up the research in quantum machine learning
• Conditional Born machine for Monte Carlo event generation
• Incremental Data-Uploading for Full-Quantum Classification
• Natural parameterized quantum circuit
• Embedding Learning in Hybrid Quantum-Classical Neural Networks
• Realization of a quantum neural network using repeat-until-success circuits in a superconducting quantum processor
• Tensor-network-assisted variational quantum algorithm
• Mitigated barren plateaus in the time-nonlocal optimization of analog quantum-algorithm protocols
• A Quantum Kernel Learning Approach to Acoustic Modeling for Spoken Command Recognition
• Single-component gradient rules for variational quantum algorithms
• Expressivity of Variational Quantum Machine Learning on the Boolean Cube
• Direct implementation of a perceptron in superconducting circuit quantum hardware
• A Quantum Hopfield Associative Memory Implemented on an Actual Quantum Processor
• Quantum variational learning for entanglement witnessing
• Characterization of variational quantum algorithms using free fermions
• Resource frugal optimizer for quantum machine learning
• Quantum Reservoir Computing for Speckle-Disorder Potentials
• Computing Graph Edit Distance with Algorithms on Quantum Devices
• Quantum-enhanced neural networks in the neural tangent kernel framework
• Hybrid quantum-classical unsupervised data clustering based on the self-organizing feature map
• Towards AutoQML: A Cloud-Based Automated Circuit Architecture Search Framework
• Quantum Algorithm for Smoothed Particle Hydrodynamics
• Efficient and quantum-adaptive machine learning with fermion neural networks
• Quantum computing quantum Monte Carlo algorithm
• Quantum Kerr Learning
• Quantum Extremal Learning
• Encoding-dependent generalization bounds for parametrized quantum circuits
• An Amplitude-Based Implementation of the Unit Step Function on a Quantum Computer
• Unitary Evolutions Sourced By Interacting Quantum Memories: Closed Quantum Systems Directing Themselves Using Their State Histories
• Learning Fourier series with parametrized quantum circuits
• Hybrid Quantum Classical Graph Neural Networks for Particle Track Reconstruction
• An Efficient Gradient Sensitive Alternate Framework for VQE with Variable Ansatz
• Witnessing Objectivity on a Quantum Computer
• An Empirical Study of Quantum Dynamics as a Ground State Problem with Neural Quantum States
• Quantum neural network autoencoder and classifier applied to an industrial case study
• Quantum Model-Discovery