The Expressive Power of Parameterized Quantum Circuits

Abstract

Parameterized quantum circuits (PQCs) have been broadly used as a hybrid quantum-classical machine learning scheme to accomplish generative tasks. However, whether PQCs have better expressive power than classical generative neural networks, such as restricted or deep Boltzmann machines, remains an open issue. In this paper, we prove that PQCs with a simple structure already outperform any classical neural network for generative tasks, unless the polynomial hierarchy collapses. Our proof builds on known results from tensor networks and quantum circuits (in particular, instantaneous quantum polynomial circuits). In addition, PQCs equipped with ancillary qubits for post-selection have even stronger expressive power than those without post-selection. We employ them as an application for Bayesian learning, since it is possible to learn prior probabilities rather than assuming they are known. We expect that it will find many more applications in semi-supervised learning where prior distributions are normally assumed to be unknown. Lastly, we conduct several numerical experiments using the Rigetti Forest platform to demonstrate the performance of the proposed Bayesian quantum circuit.

Comments welcomed!

References in corpus (8)

• The density-matrix renormalization group in the age of matrix product states
• Kernel methods in machine learning
• Quantum Computational Supremacy
• Learning phase transitions by confusion
• Quantum Data Fitting
• Quantum-enhanced machine learning
• Classical simulation of commuting quantum computations implies collapse of the polynomial hierarchy
• Variational Quantum State Diagonalization

Cited by in corpus (113)

• Variational Quantum Algorithms
• Noisy intermediate-scale quantum (NISQ) algorithms
• The power of quantum neural networks
• The effect of data encoding on the expressive power of variational quantum machine learning models
• Quantum Natural Gradient
• Robust data encodings for quantum classifiers
• Hybrid Quantum-Classical Convolutional Neural Networks
• Experimental Quantum Generative Adversarial Networks for Image Generation
• Training of Quantum Circuits on a Hybrid Quantum Computer
• Is quantum advantage the right goal for quantum machine learning?
• Quantum machine learning beyond kernel methods
• Quantum circuit architecture search for variational quantum algorithms
• Trainability of Dissipative Perceptron-Based Quantum Neural Networks
• The Born Supremacy: Quantum Advantage and Training of an Ising Born Machine
• Capacity and quantum geometry of parametrized quantum circuits
• Efficient measure for the expressivity of variational quantum algorithms
• Hybrid Quantum-Classical Generative Adversarial Network for High Resolution Image Generation
• Variational Quantum Reinforcement Learning via Evolutionary Optimization
• Quantum Machine Learning: from physics to software engineering
• Towards understanding the power of quantum kernels in the NISQ era
• Exploring the Advantages of Quantum Generative Adversarial Networks in Generative Chemistry
• Enhancing Generative Models via Quantum Correlations
• An end-to-end trainable hybrid classical-quantum classifier
• NISQ Computers: A Path to Quantum Supremacy
• Automatic design of quantum feature maps
• Perceval: A Software Platform for Discrete Variable Photonic Quantum Computing
• Learning quantum data with the quantum Earth Mover's distance
• Information Scrambling in Quantum Neural Networks
• Synergy Between Quantum Circuits and Tensor Networks: Short-cutting the Race to Practical Quantum Advantage
• Anomaly detection with variational quantum generative adversarial networks
• Generalization despite overfitting in quantum machine learning models
• Variational inference with a quantum computer
• Robust resource-efficient quantum variational ansatz through evolutionary algorithm
• Qubit-efficient encoding schemes for binary optimisation problems
• Application-Motivated, Holistic Benchmarking of a Full Quantum Computing Stack
• Expressibility and trainability of parameterized analog quantum systems for machine learning applications
• Expressivity of Quantum Neural Networks
• A Grover-search Based Quantum Learning Scheme for Classification
• Mitigating Barren Plateaus with Transfer-learning-inspired Parameter Initializations
• ResQNets: A Residual Approach for Mitigating Barren Plateaus in Quantum Neural Networks
• Tensor networks for quantum machine learning
• Quantum Transfer Learning for Real-World, Small, and High-Dimensional Datasets
• Quantum-Noise-Driven Generative Diffusion Models
• Scrambling Ability of Quantum Neural Networks Architectures
• Predicting toxicity by quantum machine learning
• Classical versus Quantum: comparing Tensor Network-based Quantum Circuits on LHC data
• Effective calculation of the Green's function in the time domain on near-term quantum processors
• Interpretable Quantum Advantage in Neural Sequence Learning
• Exponential data encoding for quantum supervised learning
• AutoQML: Automatic Generation and Training of Robust Quantum-Inspired Classifiers by Using Genetic Algorithms on Grayscale Images
• Cost function embedding and dataset encoding for machine learning with parameterized quantum circuits
• A performance characterization of quantum generative models
• Engineered dissipation to mitigate barren plateaus
• Efficient Online Quantum Generative Adversarial Learning Algorithms with Applications
• Efficient Bipartite Entanglement Detection Scheme with a Quantum Adversarial Solver
• Dequantizing quantum machine learning models using tensor networks
• Unsupervised Quantum Circuit Learning in High Energy Physics
• Quantum Quantile Mechanics: Solving Stochastic Differential Equations for Generating Time-Series
• Quantum algorithms for scientific computing
• Quantum Amplitude Amplification Operators
• Natural parameterized quantum circuit
• What can we learn from quantum convolutional neural networks?
• Quantum Latent Diffusion Models
• Quantum Continual Learning Overcoming Catastrophic Forgetting
• Towards Efficient Quantum Hybrid Diffusion Models
• Long-lived Particles Anomaly Detection with Parametrized Quantum Circuits
• Introducing Non-Linear Activations into Quantum Generative Models
• Embedding Learning in Hybrid Quantum-Classical Neural Networks
• Quantum computing Floquet energy spectra
• Optimizing Variational Quantum Algorithms with qBang: Efficiently Interweaving Metric and Momentum to Navigate Flat Energy Landscapes
• Variational Quantum Algorithms for Steady States of Open Quantum Systems
• Opportunities and challenges of quantum computing for climate modelling
• A Continuous Variable Born Machine
• Energy-dependent barren plateau in bosonic variational quantum circuits
• F-Divergences and Cost Function Locality in Generative Modelling with Quantum Circuits
• Bayesian Learning of Parameterised Quantum Circuits
• Splitting and Parallelizing of Quantum Convolutional Neural Networks for Learning Translationally Symmetric Data
• Application of the Diamond Gate in Quantum Fourier Transformations and Quantum Machine Learning
• Quantum continual learning on a programmable superconducting processor
• Quantum-enhanced neural networks in the neural tangent kernel framework
• Noise-Robust Detection of Quantum Phase Transitions
• Hype or Heuristic? Quantum Reinforcement Learning for Join Order Optimisation
• Maximising Quantum-Computing Expressive Power through Randomised Circuits
• Quantum neural compressive sensing for ghost imaging
• Generative Invertible Quantum Neural Networks
• Non-parametric Semi-Supervised Learning in Many-body Hilbert Space with Rescaled Logarithmic Fidelity
• Quantum Machine Learning in the Cognitive Domain: Alzheimer's Disease Study
• Quantum Neural Networks in Practice: A Comparative Study with Classical Models from Standard Data Sets to Industrial Images
• Approximation and Generalization Capacities of Parametrized Quantum Circuits for Functions in Sobolev Spaces
• QKAN: quantum Kolmogorov-Arnold networks with applications in machine learning and multivariate state preparation
• Transfer Learning Analysis of Variational Quantum Circuits
• Nonlinear unitary circuits for photonic neural networks
• Optimized numerical gradient and Hessian estimation for variational quantum algorithms
• Learning Fourier series with parametrized quantum circuits
• Entanglement-informed Construction of Variational Quantum Circuits
• Detecting Entanglement Generating Circuits in Cloud-Based Quantum Computing
• A Hybrid Quantum-Classical Particle-in-Cell Method for Plasma Simulations
• OnionVQE Optimization Strategy for Ground State Preparation on NISQ Devices
• Quantum Sparse Coding and Decoding Based on Quantum Network
• Quantum natural gradient with thermal-state initialization
• Expressiveness of Commutative Quantum Circuits: A Probabilistic Approach
• Single-Qudit Quantum Neural Networks for Multiclass Classification
• Enhancing Small Dataset Classification Using Projected Quantum Kernels with Convolutional Neural Networks
• Multivariate unbounded quantum regression via log-ratio probabilities mitigating barren plateaus
• LArTPC hit-based topology classification with quantum machine learning and symmetry
• Hamiltonian Expressibility for Ansatz Selection in Variational Quantum Algorithms
• Quantifying the Expressive Capacity of Quantum Systems: Fundamental Limits and Eigentasks
• Moments of Quantum Channel Ensembles
• Quantum Machine Learning for Climate Modelling
• Quantum-Inspired Weight-Constrained Neural Network: Reducing Variable Numbers by 100x Compared to Standard Neural Networks
• Hybrid Quantum-Classical Clustering for Preparing a Prior Distribution of Eigenspectrum
• Probabilistic Representation of Commutative Quantum Circuit Models
• High-expressibility Quantum Neural Networks using only classical resources