Spectral Bias in Variational Quantum Machine Learning

• URL: http://arxiv.org/abs/2506.22555v1
• Date: Fri, 27 Jun 2025 18:11:54 GMT
• Title: Spectral Bias in Variational Quantum Machine Learning
• Authors: Callum Duffy, Marcin Jastrzebski,
• Abstract summary: We study the effect specifically in parameterised quantum circuits (PQCs)<n>We find that the magnitude of the Fourier coefficients' gradients during training strongly correlates with the coefficients' redundancy.<n>We also demonstrate that PQCs with greater redundancy exhibit increased robustness to random perturbations in their parameters at the corresponding frequencies.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: In this work, we investigate the phenomenon of spectral bias in quantum machine learning, where, in classical settings, models tend to fit low-frequency components of a target function earlier during training than high-frequency ones, demonstrating a frequency-dependent rate of convergence. We study this effect specifically in parameterised quantum circuits (PQCs). Leveraging the established formulation of PQCs as Fourier series, we prove that spectral bias in this setting arises from the ``redundancy'' of the Fourier coefficients, which denotes the number of terms in the analytical form of the model contributing to the same frequency component. The choice of data encoding scheme dictates the degree of redundancy for a Fourier coefficient. We find that the magnitude of the Fourier coefficients' gradients during training strongly correlates with the coefficients' redundancy. We then further demonstrate this empirically with three different encoding schemes. Additionally, we demonstrate that PQCs with greater redundancy exhibit increased robustness to random perturbations in their parameters at the corresponding frequencies. We investigate how design choices affect the ability of PQCs to learn Fourier sums, focusing on parameter initialization scale and entanglement structure, finding large initializations and low-entanglement schemes tend to slow convergence.

Related papers

• Out of Tune: Demystifying Noise-Effects on Quantum Fourier Models [2.4456747580554157]
  We systematically analyse the effect of noise on the Fourier spectrum, expressibility and entangling capability of quantum systems.<n>We find that decoherent noise exerts a uniform deleterious effect on all the tested ans"atze.<n>This may help to better utilise hardware resources, and guide the construction of tailored error correction schemes.
  arXiv  Detail & Related papers  (2025-06-11T08:52:31Z)
• Spectral truncation of out-of-time-ordered correlators in dissipative system [44.99833362998488]
  Out-of-time-ordered correlators (OTOCs) have emerged as powerful tools for diagnosing quantum chaos and information scrambling.<n>We investigate the spectral decomposition of OTOCs in open quantum systems using the dissipative modified kicked rotator (DMKR) as a paradigmatic model.<n>Our results provide a quantitative framework for understanding OTOCs in dissipative quantum systems and suggest new avenues for experimental exploration in open quantum platforms.
  arXiv  Detail & Related papers  (2025-03-05T17:22:25Z)
• Holistic Physics Solver: Learning PDEs in a Unified Spectral-Physical Space [54.13671100638092]
  Holistic Physics Mixer (HPM) is a framework for integrating spectral and physical information in a unified space.<n>We show that HPM consistently outperforms state-of-the-art methods in both accuracy and computational efficiency.
  arXiv  Detail & Related papers  (2024-10-15T08:19:39Z)
• Fourier Neural Operators for Learning Dynamics in Quantum Spin Systems [77.88054335119074]
  We use FNOs to model the evolution of random quantum spin systems. We apply FNOs to a compact set of Hamiltonian observables instead of the entire $2n$ quantum wavefunction.
  arXiv  Detail & Related papers  (2024-09-05T07:18:09Z)
• Fourier Series Guided Design of Quantum Convolutional Neural Networks for Enhanced Time Series Forecasting [0.9060149007362646]
  We apply 1D quantum convolution to address the task of time series forecasting. By encoding multiple points into the quantum circuit to predict subsequent data, each point becomes a feature, transforming the problem into a multidimensional one.
  arXiv  Detail & Related papers  (2024-04-23T01:35:07Z)
• Utilizing Quantum Processor for the Analysis of Strongly Correlated Materials [34.63047229430798]
  This study introduces a systematic approach for analyzing strongly correlated systems by adapting the conventional quantum cluster method to a quantum circuit model. We have developed a more concise formula for calculating the cluster's Green's function, requiring only real-number computations on the quantum circuit instead of complex ones.
  arXiv  Detail & Related papers  (2024-04-03T06:53:48Z)
• Constrained and Vanishing Expressivity of Quantum Fourier Models [2.7746258981078196]
  We show a new correlation between the Fourier coefficients of the quantum model and its encoding gates. We also show a phenomenon of vanishing expressivity in certain settings. These two behaviors imply novel forms of constraints which limit the expressivity of PQCs.
  arXiv  Detail & Related papers  (2024-03-14T14:05:24Z)
• Let Quantum Neural Networks Choose Their Own Frequencies [0.0]
  We generalize 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.
  arXiv  Detail & Related papers  (2023-09-06T18:00:07Z)
• Quantum Effects on the Synchronization Dynamics of the Kuramoto Model [62.997667081978825]
  We show that quantum fluctuations hinder the emergence of synchronization, albeit not entirely suppressing it. We derive an analytical expression for the critical coupling, highlighting its dependence on the model parameters.
  arXiv  Detail & Related papers  (2023-06-16T16:41:16Z)
• Incremental Spatial and Spectral Learning of Neural Operators for Solving Large-Scale PDEs [86.35471039808023]
  We introduce the Incremental Fourier Neural Operator (iFNO), which progressively increases the number of frequency modes used by the model. We show that iFNO reduces total training time while maintaining or improving generalization performance across various datasets. Our method demonstrates a 10% lower testing error, using 20% fewer frequency modes compared to the existing Fourier Neural Operator, while also achieving a 30% faster training.
  arXiv  Detail & Related papers  (2022-11-28T09:57:15Z)
• Momentum Diminishes the Effect of Spectral Bias in Physics-Informed Neural Networks [72.09574528342732]
  Physics-informed neural network (PINN) algorithms have shown promising results in solving a wide range of problems involving partial differential equations (PDEs) They often fail to converge to desirable solutions when the target function contains high-frequency features, due to a phenomenon known as spectral bias. In the present work, we exploit neural tangent kernels (NTKs) to investigate the training dynamics of PINNs evolving under gradient descent with momentum (SGDM)
  arXiv  Detail & Related papers  (2022-06-29T19:03:10Z)
• Sigma-Delta and Distributed Noise-Shaping Quantization Methods for Random Fourier Features [73.25551965751603]
  We prove that our quantized RFFs allow a high accuracy approximation of the underlying kernels. We show that the quantized RFFs can be further compressed, yielding an excellent trade-off between memory use and accuracy. We empirically show by testing the performance of our methods on several machine learning tasks that our method compares favorably to other state of the art quantization methods in this context.
  arXiv  Detail & Related papers  (2021-06-04T17:24:47Z)
• Quadratic-exponential functionals of Gaussian quantum processes [1.7360163137925997]
  quadratic-exponential functionals (QEFs) arise as robust performance criteria in control problems. We develop a randomised representation for the QEF using a Karhunen-Loeve expansion of the quantum process. For stationary Gaussian quantum processes, we establish a frequency-domain formula for the QEF rate.
  arXiv  Detail & Related papers  (2021-03-16T18:58:39Z)
• Characterizing the loss landscape of variational quantum circuits [77.34726150561087]
  We introduce a way to compute the Hessian of the loss function of VQCs. We show how this information can be interpreted and compared to classical neural networks.
  arXiv  Detail & Related papers  (2020-08-06T17:48:12Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.