Expressivity of Quantum Neural Networks

Abstract

In this work, we address the question whether a sufficiently deep quantum neural network can approximate a target function as accurate as possible. We start with simple but typical physical situations that the target functions are physical observables, and then we extend our discussion to situations that the learning targets are not directly physical observables, but can be expressed as physical observables in an enlarged Hilbert space with multiple replicas, such as the Loshimidt echo and the Renyi entropy. The main finding is that an accurate approximation is possible only when the input wave functions in the dataset do not exhaust the entire Hilbert space that the quantum circuit acts on, and more precisely, the Hilbert space dimension of the former has to be less than half of the Hilbert space dimension of the latter. In some cases, this requirement can be satisfied automatically because of the intrinsic properties of the dataset, for instance, when the input wave function has to be symmetric between different replicas. And if this requirement cannot be satisfied by the dataset, we show that the expressivity capabilities can be restored by adding one ancillary qubit where the wave function is always fixed at input. Our studies point toward establishing a quantum neural network analogy of the universal approximation theorem that lays the foundation for expressivity of classical neural networks.

References in corpus (23)

• Quantum Computing in the NISQ era and beyond
• Quantum Machine Learning
• Barren plateaus in quantum neural network training landscapes
• Quantum Circuit Learning
• Quantum Convolutional Neural Networks
• Circuit-centric quantum classifiers
• Efficient Learning for Deep Quantum Neural Networks
• Quantum autoencoders for efficient compression of quantum data
• A generative modeling approach for benchmarking and training shallow quantum circuits
• Hierarchical quantum classifiers
• The Expressive Power of Parameterized Quantum Circuits
• Towards Quantum Machine Learning with Tensor Networks
• Differentiable Learning of Quantum Circuit Born Machine
• Quantum autoencoders to denoise quantum data
• Quantum-Assisted Learning of Hardware-Embedded Probabilistic Graphical Models
• Experimental Realization of a Quantum Autoencoder: The Compression of Qutrits via Machine Learning
• Unitary quantum perceptron as efficient universal approximator
• Learning and Inference on Generative Adversarial Quantum Circuits
• Information Scrambling in Quantum Neural Networks
• Quantum machine learning and quantum biomimetics: A perspective
• Nonlinear Quantum Neuron: A Fundamental Building Block for Quantum Neural Networks
• Making Trotters Sprint: A Variational Imaginary Time Ansatz for Quantum Many-body Systems
• The Quantum Cocktail Party Problem

Cited by in corpus (16)

• Is quantum advantage the right goal for quantum machine learning?
• Efficient measure for the expressivity of variational quantum algorithms
• Recent advances for quantum classifiers
• Understanding quantum machine learning also requires rethinking generalization
• Quantum Neural Network Classifiers: A Tutorial
• Tackling Sampling Noise in Physical Systems for Machine Learning Applications: Fundamental Limits and Eigentasks
• Randomness-enhanced expressivity of quantum neural networks
• Towards Efficient Quantum Hybrid Diffusion Models
• Fermionic Simulators for Enhanced Scalability of Variational Quantum Simulation
• Enhanced feature encoding and classification on distributed quantum hardware
• Universal Approximation Theorem and error bounds for quantum neural networks and quantum reservoirs
• Generative Invertible Quantum Neural Networks
• Optimal depth and a novel approach to variational quantum process tomography
• Learning Fourier series with parametrized quantum circuits
• Benchmarking of quantum fidelity kernels for Gaussian process regression
• Measuring Incompatible Observables with Quantum Neural Networks