Challenges
Datasets
Workspaces
Papers
Discussions
Leaderboard
Log inSign up
Challenges
Datasets
Workspaces
Papers
Discussions
Leaderboard
Blog
Job Board
Q3AS

© 2026 Aqora Quantum S.A.S.

TermsPrivacyLegal Notice

arXiv:2508.20868 · Quantum Science and Technology

Fourier fingerprints of ansatzes in quantum machine learning

Melvin Strobl, M Emre Sahin, Lucas van der Horst, Eileen Kuehn, Achim Streit, Ben Jaderberg

Published Jul 21, 2026• 13 citations
arXivHTMLPDF

Abstract

Abstract Typical schemes to encode classical data in variational quantum machine learning (QML) lead to quantum Fourier models with O ( exp ⁡ ( n ) ) Fourier basis functions in the number of qubits. Despite this, in order for the model to be efficiently trainable, the number of parameters must scale as O ( poly ( n ) ) . This imbalance implies the existence of correlations between the Fourier modes, which depend on the structure of the circuit. In this work, we demonstrate that this phenomenon exists and show cases where these correlations can be used to predict ansatz performance. For several popular ansatzes, we compute the Fourier coefficient correlations (FCCs) using a linear feature map (FM) and construct the Fourier fingerprint , a visual representation of the correlation structure. We subsequently numerically show how, for the problem of learning random Fourier series, the FCC correctly predicts relative performance of ansatzes whilst the widely-used expressibility metric does not. Finally, we demonstrate how our framework applies to the more challenging problem of jet reconstruction in high-energy physics. Overall, our results demonstrate how the Fourier fingerprint is a powerful new tool in the problem of optimal ansatz choice for QML.

DOI
10.1088/2058-9565/ae8df8

Related papers

Beyond Gates: Pulse Level Quantum Fourier Models

Melvin Strobl, Maja Franz, Lukas Scheller +3 more

In the domain of variational quantum algorithms, quantum Fourier models (QFMs) provide a mathematically well defined structure for quantum machine learning (QML). There has been a substantial amount of work on the scalability and trainability of such models showcasing the potential but also the limitations for the prospective application of QFMs. However, much less is known in the context of pulse-level quantum computing, where the microwave parameters that implement unitary operations on the hardware are used to perform computations directly instead of through the interface of quantum circuits. In this work, we evaluate QFMs through the lens of pulse parameters and link metrics such as expressibility and Fourier coefficient correlation (FCC) to this extended set of variational parameters. We show that while control over pulse shapes does not significantly alter the global expressibility or structural correlations of the Ansatz, it fundamentally alters the local optimisation landscape. For composite gates, independent pulse scalings replace a single logical angle by multiple independently tunable sub-angles. This relaxes the rigid monomial couplings induced by the gate-level parameterisation, and provides gradient descent with higher-dimensional escape routes, decoupling local parameter constraints and significantly boosting performance during training. Following an analytical proof, we show numerical results validating our theory on training a QFM with an exponential (ternary) feature map on a Fourier series with the same frequencies.

quant-pharXiv:2605.04945•May 7, 2026•1 citation

Spectral Bias in Variational Quantum Machine Learning

Callum Duffy, Marcin Jastrzebski

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.

arXiv:2506.22555•Jun 27, 2025•16 citations

Fourier series guided design of quantum convolutional neural networks for enhanced time series forecasting

Sandra Leticia Juárez-Osorio, Mayra Alejandra Rivera-Ruiz, Andres Méndez-Vázquez +2 more

Abstract In this work, we explore the application of 1D quantum convolutional layers for time series forecasting, framing the problem within the context of machine learning and quantum circuit expressivity. By encoding multiple time steps as features into a quantum circuit, the forecasting task becomes intrinsically multidimensional. We leverage the recent theoretical results that describe Variational Quantum Circuits (VQCs) as multidimensional Fourier series, to design a more expressive 1D quantum convolutional neural network in which an enhanced performance is obtained by reuploading the data. We aim to relate the number of accessible coefficients in each architecture design with the obtained metrics. Our analysis incorporates key machine learning concepts such as expressivity and the presence of barren plateaus, evaluating their impact on generalization and training efficiency. Notably, we show that even with a limited number of trainable parameters, quantum circuits can approximate high-degree Fourier functions, underscoring their expressive capacity and computational efficiency. Our results demonstrate that more expressive ansatz, characterized by richer Fourier spectra, consistently yield improved predictive performance as the number of qubits increases. This study bridges theoretical insights from quantum physics with practical advances in machine learning model design for time series forecasting.

Physica Scripta•Oct 1, 2025•2 citations

Fourier Series Guided Design of Quantum Convolutional Neural Networks for Enhanced Time Series Forecasting]{Fourier Series Guided Design of Quantum Convolutional Neural Networks for Enhanced Time Series Forecasting

Sandra Leticia Juárez-Osorio, Mayra Alejandra Rivera-Ruiz, Andres Méndez-Vázquez +2 more

Abstract In this work, we apply 1D quantum convolution in the task of time series forecasting. By encoding multiple points into the quantum circuit to predict subsequent data, each point becomes a feature and the problem becomes a multidimensional one. Taking as basis previous theoretical works which demonstrated that Variational Quantum Circuits (VQCs) can be expressed as multidimensional Fourier series, the capabilities of different architectures and ansatz are explored. This analysis considers the concepts of circuit expressivity and the presence of barren plateaus. Analyzing the problem within the framework of the Fourier series enabled the incorporation of data reuploading in the architecture, resulting in enhanced performance. Rather than a strict requirement for the number of free parameters to exceed the degrees of freedom of the Fourier series, our findings suggest that even a limited number of parameters can produce Fourier functions of higher degrees. This highlights the remarkable expressive power of quantum circuits. This observation is also significant in reducing training times. The ansatz with greater expressivity and number of non-zero Fourier coefficients consistently delivers favorable results across different scenarios, with performance metrics improving as the number of qubits increases.

•Sep 9, 2024•0 citations

Exploring Trainability of Quantum Fourier Models for a Data-Tailored Encoding Scheme

Felix Paul, Peter Jung, Björn Minneker

Quantum Machine Learning (QML) models have shown great promise in solving complex problems, but their expressivity and trainability is often limited by the choice of architecture. In the Fourier framework, layer-dependent data re-uploading has been proposed to increase expressivity, but applying this scheme often results in a trade-off between generalizability and trainability. By ensuring that the redundancies of some frequencies in the Fourier spectrum are high when selecting an encoding, the flexibility of the corresponding coefficients is increased, which in turn influences the trainability of the model. In this work we empirically investigate how a data-tailored re-uploading scheme affects trainability of QML models and find an indication for better performing models.

IEEE International Conference on Acoustics Speech and Signal Processing•Apr 21, 2026•0 citations

Efficient MPS representations and quantum circuits from the Fourier modes of classical image data

Bernhard Jobst, Kevin Shen, Carlos A. Riofrío +2 more

Machine learning tasks are an exciting application for quantum computers, as it has been proven that they can learn certain problems more efficiently than classical ones. Applying quantum machine learning algorithms to classical data can have many important applications, as qubits allow for dealing with exponentially more data than classical bits. However, preparing the corresponding quantum states usually requires an exponential number of gates and therefore may ruin any potential quantum speedups. Here, we show that classical data with a sufficiently quickly decaying Fourier spectrum after being mapped to a quantum state can be well-approximated by states with a small Schmidt rank (i.e., matrix-product states) and we derive explicit error bounds. These approximated states can, in turn, be prepared on a quantum computer with a linear number of nearest-neighbor two-qubit gates. We confirm our results numerically on a set of 1024 × 1024 -pixel images taken from the `Imagenette' and DIV2K datasets. Additionally, we consider different variational circuit ansätze and demonstrate numerically that one-dimensional sequential circuits achieve the same compression quality as more powerful ansätze.

arXiv:2311.07666•Quantum•Dec 3, 2024•28 citations
Abstract Typical schemes to encode classical data in variational quantum machine learning (QML) lead to quantum Fourier models with O ( exp ⁡ ( n ) ) Fourier basis functions in the number of qubits. Despite this, in order for the model to be efficiently trainable, the number of parameters must scale as O ( poly ( n ) ) . This imbalance implies the existence of correlations between the Fourier modes, which depend on the structure of the circuit. In this work, we demonstrate that this phenomenon exists and show cases where these correlations can be used to predict ansatz performance. For several popular ansatzes, we compute the Fourier coefficient correlations (FCCs) using a linear feature map (FM) and construct the Fourier fingerprint , a visual representation of the correlation structure. We subsequently numerically show how, for the problem of learning random Fourier series, the FCC correctly predicts relative performance of ansatzes whilst the widely-used expressibility metric does not. Finally, we demonstrate how our framework applies to the more challenging problem of jet reconstruction in high-energy physics. Overall, our results demonstrate how the Fourier fingerprint is a powerful new tool in the problem of optimal ansatz choice for QML.
In the domain of variational quantum algorithms, quantum Fourier models (QFMs) provide a mathematically well defined structure for quantum machine learning (QML). There has been a substantial amount of work on the scalability and trainability of such models showcasing the potential but also the limitations for the prospective application of QFMs. However, much less is known in the context of pulse-level quantum computing, where the microwave parameters that implement unitary operations on the hardware are used to perform computations directly instead of through the interface of quantum circuits. In this work, we evaluate QFMs through the lens of pulse parameters and link metrics such as expressibility and Fourier coefficient correlation (FCC) to this extended set of variational parameters. We show that while control over pulse shapes does not significantly alter the global expressibility or structural correlations of the Ansatz, it fundamentally alters the local optimisation landscape. For composite gates, independent pulse scalings replace a single logical angle by multiple independently tunable sub-angles. This relaxes the rigid monomial couplings induced by the gate-level parameterisation, and provides gradient descent with higher-dimensional escape routes, decoupling local parameter constraints and significantly boosting performance during training. Following an analytical proof, we show numerical results validating our theory on training a QFM with an exponential (ternary) feature map on a Fourier series with the same frequencies.
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.
Abstract In this work, we explore the application of 1D quantum convolutional layers for time series forecasting, framing the problem within the context of machine learning and quantum circuit expressivity. By encoding multiple time steps as features into a quantum circuit, the forecasting task becomes intrinsically multidimensional. We leverage the recent theoretical results that describe Variational Quantum Circuits (VQCs) as multidimensional Fourier series, to design a more expressive 1D quantum convolutional neural network in which an enhanced performance is obtained by reuploading the data. We aim to relate the number of accessible coefficients in each architecture design with the obtained metrics. Our analysis incorporates key machine learning concepts such as expressivity and the presence of barren plateaus, evaluating their impact on generalization and training efficiency. Notably, we show that even with a limited number of trainable parameters, quantum circuits can approximate high-degree Fourier functions, underscoring their expressive capacity and computational efficiency. Our results demonstrate that more expressive ansatz, characterized by richer Fourier spectra, consistently yield improved predictive performance as the number of qubits increases. This study bridges theoretical insights from quantum physics with practical advances in machine learning model design for time series forecasting.
Abstract In this work, we apply 1D quantum convolution in the task of time series forecasting. By encoding multiple points into the quantum circuit to predict subsequent data, each point becomes a feature and the problem becomes a multidimensional one. Taking as basis previous theoretical works which demonstrated that Variational Quantum Circuits (VQCs) can be expressed as multidimensional Fourier series, the capabilities of different architectures and ansatz are explored. This analysis considers the concepts of circuit expressivity and the presence of barren plateaus. Analyzing the problem within the framework of the Fourier series enabled the incorporation of data reuploading in the architecture, resulting in enhanced performance. Rather than a strict requirement for the number of free parameters to exceed the degrees of freedom of the Fourier series, our findings suggest that even a limited number of parameters can produce Fourier functions of higher degrees. This highlights the remarkable expressive power of quantum circuits. This observation is also significant in reducing training times. The ansatz with greater expressivity and number of non-zero Fourier coefficients consistently delivers favorable results across different scenarios, with performance metrics improving as the number of qubits increases.
Quantum Machine Learning (QML) models have shown great promise in solving complex problems, but their expressivity and trainability is often limited by the choice of architecture. In the Fourier framework, layer-dependent data re-uploading has been proposed to increase expressivity, but applying this scheme often results in a trade-off between generalizability and trainability. By ensuring that the redundancies of some frequencies in the Fourier spectrum are high when selecting an encoding, the flexibility of the corresponding coefficients is increased, which in turn influences the trainability of the model. In this work we empirically investigate how a data-tailored re-uploading scheme affects trainability of QML models and find an indication for better performing models.
Machine learning tasks are an exciting application for quantum computers, as it has been proven that they can learn certain problems more efficiently than classical ones. Applying quantum machine learning algorithms to classical data can have many important applications, as qubits allow for dealing with exponentially more data than classical bits. However, preparing the corresponding quantum states usually requires an exponential number of gates and therefore may ruin any potential quantum speedups. Here, we show that classical data with a sufficiently quickly decaying Fourier spectrum after being mapped to a quantum state can be well-approximated by states with a small Schmidt rank (i.e., matrix-product states) and we derive explicit error bounds. These approximated states can, in turn, be prepared on a quantum computer with a linear number of nearest-neighbor two-qubit gates. We confirm our results numerically on a set of 1024 × 1024 -pixel images taken from the `Imagenette' and DIV2K datasets. Additionally, we consider different variational circuit ansätze and demonstrate numerically that one-dimensional sequential circuits achieve the same compression quality as more powerful ansätze.