Multidimensional Fourier series with quantum circuits

Abstract

Quantum machine learning is the field that aims to integrate machine learning with quantum computation. In recent years, the field has emerged as an active research area with the potential to bring new insights to classical machine learning problems. One of the challenges in the field is to explore the expressibility of parametrized quantum circuits and their ability to be universal function approximators, as classical neural networks are. Recent works have shown that with a quantum supervised learning model, we can fit any one-dimensional Fourier series, proving their universality. However, models for multidimensional functions have not been explored in the same level of detail. In this work, we study the expressibility of various types of circuit ansatzes that generate multidimensional Fourier series. We found that, for some ansatzes, the degrees of freedom required for fitting such functions grow faster than the available degrees in the Hilbert space generated by the circuits. For example, single-qudit models have limited power to represent arbitrary multidimensional Fourier series. Despite this, we show that we can enlarge the Hilbert space of the circuit by using more qudits or higher local dimensions to meet the degrees of freedom requirements, thus ensuring the universality of the models.

arXiv comment8 pages, 5 figures + appendices

References in corpus (15)

• Quantum Computing in the NISQ era and beyond
• Quantum Machine Learning
• Variational Quantum Algorithms
• Noisy intermediate-scale quantum (NISQ) algorithms
• The effect of data encoding on the expressive power of variational quantum machine learning models
• Data re-uploading for a universal quantum classifier
• Advances in High Dimensional Quantum Entanglement
• Quantum Information Scrambling in a Superconducting Qutrit Processor
• Three addressable spin qubits in a molecular single-ion magnet
• Experimental high-dimensional Greenberger-Horne-Zeilinger entanglement with superconducting transmon qutrits
• Qutrit Entanglement
• Universal Approximation Property of Quantum Machine Learning Models in Quantum-Enhanced Feature Spaces
• One qubit as a Universal Approximant
• Exponential data encoding for quantum supervised learning
• Fock State-enhanced Expressivity of Quantum Machine Learning Models

Cited by in corpus (18)

• Shadows of quantum machine learning
• Fourier expansion in variational quantum algorithms
• Dequantizing quantum machine learning models using tensor networks
• Neural quantum kernels: training quantum kernels with quantum neural networks
• Quantum Fourier Iterative Amplitude Estimation
• Qudit Machine Learning
• Satellite image classification with neural quantum kernels
• Density Matrix Emulation of Quantum Recurrent Neural Networks for Multivariate Time Series Prediction
• Loop Feynman integration on a quantum computer
• Barren plateaus are swamped with traps
• A Quantum Algorithmic Approach to Multiconfigurational Valence Bond Theory: Insights from Interpretable Circuit Design
• Quantum integration of decay rates at second order in perturbation theory
• Learning Fourier series with parametrized quantum circuits
• Approximation and Generalization Capacities of Parametrized Quantum Circuits for Functions in Sobolev Spaces
• Expressivity of deterministic quantum computation with one qubit
• Expressiveness of Commutative Quantum Circuits: A Probabilistic Approach
• Universal approximation of continuous functions with minimal quantum circuits
• Quantum Machine Learning for Climate Modelling