Let Quantum Neural Networks Choose Their Own Frequencies

Abstract

Parameterized quantum circuits as machine learning models are typically well described by their representation as a partial Fourier series of the input features, with frequencies uniquely determined by the feature map's generator Hamiltonians. Ordinarily, these data-encoding generators are chosen in advance, fixing the space of functions that can be represented. In this work we consider a generalization of quantum models to include a set of trainable parameters in the generator, leading to a trainable frequency (TF) quantum model. We numerically demonstrate how TF models can learn generators with desirable properties for solving the task at hand, including non-regularly spaced frequencies in their spectra and flexible spectral richness. Finally, we showcase the real-world effectiveness of our approach, demonstrating an improved accuracy in solving the Navier-Stokes equations using a TF model with only a single parameter added to each encoding operation. Since TF models encompass conventional fixed frequency models, they may offer a sensible default choice for variational quantum machine learning.

11 pages, 7 figures. Updated with small changes for publication

References in corpus (13)

• Quantum algorithm for solving linear systems of equations
• The effect of data encoding on the expressive power of variational quantum machine learning models
• A rigorous and robust quantum speed-up in supervised machine learning
• Quantum machine learning beyond kernel methods
• Quantum agents in the Gym: a variational quantum algorithm for deep Q-learning
• Solving nonlinear differential equations with differentiable quantum circuits
• Exploiting symmetry in variational quantum machine learning
• Training Quantum Embedding Kernels on Near-Term Quantum Computers
• Representation Learning via Quantum Neural Tangent Kernels
• Generalization despite overfitting in quantum machine learning models
• Quantum Kernel Methods for Solving Differential Equations
• A super-polynomial quantum-classical separation for density modelling
• Single-component gradient rules for variational quantum algorithms

Cited by in corpus (8)

• Training robust and generalizable quantum models
• Constrained and Vanishing Expressivity of Quantum Fourier Models
• Quantum Neural Networks in Practice: A Comparative Study with Classical Models from Standard Data Sets to Industrial Images
• Fourier Analysis of Variational Quantum Circuits for Supervised Learning
• QUACK: Quantum Aligned Centroid Kernel
• A Hybrid Quantum-Classical Particle-in-Cell Method for Plasma Simulations
• Expressivity of deterministic quantum computation with one qubit
• Vortex Detection from Quantum Data