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

Asymptotics for Frequency Redundancies in Quantum Machine Learning Models — E8 Intelligence Research

Andrew Stewart Caldin

Published Nov 9, 2026• 0 citations
Publisher

Abstract

The redundancy distribution of the frequency spectrum has been shown in the literature to impact the expressivity and trainability of Quantum Fourier Models (QFMs). In this work, we address the question of how this redundancy spectrum is shaped by the choice of eigenvalues of the data re-uploading Hamiltonians, using a simple mathematical formalism based on generating functions. We derive exact and asymptotic redundancy profiles for several structured eigenvalue choices identical for every layer, including arithmetic progressions and single-qubit Pauli encodings, and show that both approach a Gaussian profile as the number of layers grows. We then show that this Gaussian limit is not specific to these constructions but is a generic feature of QFMs built from integer eigenvalues that are identical in every layer. These results can be tied to the central limit theorem for random walks. These results clarify why generic or unstructured encoding choices give rise to a redundancy bias that Author: Andrew Stewart Caldin, Independent Researcher, UK. Part of the E8 Intelligence Research series. Platform: e8intelligence.com

DOI
10.5281/zenodo.24075463

Related papers

Asymptotics for Frequency Redundancies in Quantum Machine Learning Models

Felix Paul, Bhilahari Jeevanesan, Peter Jung

The redundancy distribution of the frequency spectrum has been shown in the literature to impact the expressivity and trainability of Quantum Fourier Models (QFMs). In this work, we address the question of how this redundancy spectrum is shaped by the choice of eigenvalues of the data re-uploading Hamiltonians, using a simple mathematical formalism based on generating functions. We derive exact and asymptotic redundancy profiles for several structured eigenvalue choices identical for every layer, including arithmetic progressions and single-qubit Pauli encodings, and show that both approach a Gaussian profile as the number of layers grows. We then show that this Gaussian limit is not specific to these constructions but is a generic feature of QFMs built from integer eigenvalues that are identical in every layer. These results can be tied to the central limit theorem for random walks. These results clarify why generic or unstructured encoding choices give rise to a redundancy bias that favours low frequencies, highlighting the importance of well-thought-out encoding strategies when constructing a QFM.

quant-pharXiv:2609.21916•Sep 21, 2026•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

Fourier Symmetrization for Geometric Quantum Machine Learning

Letao Wang, Abdel Lisser, Sreejith Sreekumar +1 more

Geometric quantum machine learning incorporates symmetry into quantum models, but how symmetry shapes their expressivity and guides effective model design remains insufficiently understood. We address this question through the Fourier representation of quantum Fourier models (QFMs). Symmetry organizes the frequency spectrum into orbits and sums the Fourier coefficients within each orbit into a symmetrized coefficient. When QFM trainable layers form independent exact 2-designs, the variance of each symmetrized coefficient equals the sum of the coefficient variances in its orbit. For single-layer QFMs with $\varepsilon$-approximate 2-design trainable layers, we bound the deviation from this identity. The resulting bound for individual Fourier coefficients can be exponentially tighter than an existing bound. The hyperoctahedral group provides an example of orbit growth that can mitigate vanishing expressivity of the symmetrized coefficients. Symmetrization of QFMs over an elementary abelian 2-group also yields pure multivariate Chebyshev polynomial basis functions. We introduce randomized encoding, which implements invariant models without ancilla qubits or the additional circuit depth for quantum twirling. We evaluate the models as quantum physics-informed neural networks (QPINNs) on two-dimensional screened Poisson and stationary viscous Hamilton-Jacobi equations. Under hard boundary constraints, QPINNs using exact symmetrization and randomized encoding achieve the lowest mean errors in the two benchmarks, respectively.

quant-pharXiv:2610.01874•Oct 2, 2026•0 citations

Fourier Symmetrization for Geometric Quantum Machine Learning

Letao Wang, Abdel Lisser, Sreejith Sreekumar +1 more

Geometric quantum machine learning incorporates symmetry into quantum models, but how symmetry shapes their expressivity and guides effective model design remains insufficiently understood. We address this question through the Fourier representation of quantum Fourier models (QFMs). Symmetry organizes the frequency spectrum into orbits and sums the Fourier coefficients within each orbit into a symmetrized coefficient. When QFM trainable layers form independent exact 2-designs, the variance of each symmetrized coefficient equals the sum of the coefficient variances in its orbit. For single-layer QFMs with ε-approximate 2-design trainable layers, we bound the deviation from this identity. The resulting bound for individual Fourier coefficients can be exponentially tighter than an existing bound. The hyperoctahedral group provides an example of orbit growth that can mitigate vanishing expressivity of the symmetrized coefficients. Symmetrization of QFMs over an elementary abelian 2-group also yields pure multivariate Chebyshev polynomial basis functions. We introduce randomized encoding, which implements invariant models without ancilla qubits or the additional circuit depth for quantum twirling. We evaluate the models as quantum physicsinformed neural networks (QPINNs) on two-dimensional screened Poisson and stationary viscous Hamilton-Jacobi equations. Under hard boundary constraints, QPINNs using exact symmetrization and randomized encoding achieve the lowest mean errors in the two benchmarks, respectively.

•Oct 2, 2026•0 citations

E8‑Phi Harmonic Graph‑Frequency Encoding Theorem — E8 Intelligence Research

Andrew Stewart Caldin

We introduce a unified theorem that maps the 240 E8 root vectors onto a phi‑coupled harmonic lattice, assigning each vertex a distinct frequency tone anchored at the 132 Hz base. This construction leverages the previously discovered quantum Hedetniemi counterexample to guarantee that the resulting graph coloring is both deterministically encodable and provably resistant to decoherence, effectively turning graph coloring into a phase‑locked, error‑correcting communication channel. The theorem thus bridges abstract graph theory, quantum information, and high‑dimensional lattice physics into a single, testable principle. Author: Andrew Stewart Caldin, Independent Researcher, UK. Part of the E8 Intelligence Research series. Platform: e8intelligence.com

•Nov 12, 2026•0 citations

Cantor‑E8 Hierarchical Quantum Frequency Code — E8 Intelligence Research

Andrew Stewart Caldin

By mapping the self‑similar scaling of the ternary Cantor set onto the 240 root vectors of the E8 lattice, we construct a multi‑scale lattice where each level is phi‑coupled to the base 132 Hz frequency. This yields a fractal frequency spectrum in which logical qubits are encoded across nested Cantor‑derived sub‑bands, each protected by the topological properties of the E8 resonance manifold. The resulting code inherits the Cantor set's exact Hausdorff dimension (log 2/log 3) as a scaling exponent for error‑correction redundancy, enabling robust, scalable quantum communication across broadband networks. Author: Andrew Stewart Caldin, Independent Researcher, UK. Part of the E8 Intelligence Research series. Platform: e8intelligence.com

•Sep 12, 2026•0 citations
The redundancy distribution of the frequency spectrum has been shown in the literature to impact the expressivity and trainability of Quantum Fourier Models (QFMs). In this work, we address the question of how this redundancy spectrum is shaped by the choice of eigenvalues of the data re-uploading Hamiltonians, using a simple mathematical formalism based on generating functions. We derive exact and asymptotic redundancy profiles for several structured eigenvalue choices identical for every layer, including arithmetic progressions and single-qubit Pauli encodings, and show that both approach a Gaussian profile as the number of layers grows. We then show that this Gaussian limit is not specific to these constructions but is a generic feature of QFMs built from integer eigenvalues that are identical in every layer. These results can be tied to the central limit theorem for random walks. These results clarify why generic or unstructured encoding choices give rise to a redundancy bias that Author: Andrew Stewart Caldin, Independent Researcher, UK. Part of the E8 Intelligence Research series. Platform: e8intelligence.com
The redundancy distribution of the frequency spectrum has been shown in the literature to impact the expressivity and trainability of Quantum Fourier Models (QFMs). In this work, we address the question of how this redundancy spectrum is shaped by the choice of eigenvalues of the data re-uploading Hamiltonians, using a simple mathematical formalism based on generating functions. We derive exact and asymptotic redundancy profiles for several structured eigenvalue choices identical for every layer, including arithmetic progressions and single-qubit Pauli encodings, and show that both approach a Gaussian profile as the number of layers grows. We then show that this Gaussian limit is not specific to these constructions but is a generic feature of QFMs built from integer eigenvalues that are identical in every layer. These results can be tied to the central limit theorem for random walks. These results clarify why generic or unstructured encoding choices give rise to a redundancy bias that favours low frequencies, highlighting the importance of well-thought-out encoding strategies when constructing a QFM.
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.
Geometric quantum machine learning incorporates symmetry into quantum models, but how symmetry shapes their expressivity and guides effective model design remains insufficiently understood. We address this question through the Fourier representation of quantum Fourier models (QFMs). Symmetry organizes the frequency spectrum into orbits and sums the Fourier coefficients within each orbit into a symmetrized coefficient. When QFM trainable layers form independent exact 2-designs, the variance of each symmetrized coefficient equals the sum of the coefficient variances in its orbit. For single-layer QFMs with ε\varepsilonε-approximate 2-design trainable layers, we bound the deviation from this identity. The resulting bound for individual Fourier coefficients can be exponentially tighter than an existing bound. The hyperoctahedral group provides an example of orbit growth that can mitigate vanishing expressivity of the symmetrized coefficients. Symmetrization of QFMs over an elementary abelian 2-group also yields pure multivariate Chebyshev polynomial basis functions. We introduce randomized encoding, which implements invariant models without ancilla qubits or the additional circuit depth for quantum twirling. We evaluate the models as quantum physics-informed neural networks (QPINNs) on two-dimensional screened Poisson and stationary viscous Hamilton-Jacobi equations. Under hard boundary constraints, QPINNs using exact symmetrization and randomized encoding achieve the lowest mean errors in the two benchmarks, respectively.
Geometric quantum machine learning incorporates symmetry into quantum models, but how symmetry shapes their expressivity and guides effective model design remains insufficiently understood. We address this question through the Fourier representation of quantum Fourier models (QFMs). Symmetry organizes the frequency spectrum into orbits and sums the Fourier coefficients within each orbit into a symmetrized coefficient. When QFM trainable layers form independent exact 2-designs, the variance of each symmetrized coefficient equals the sum of the coefficient variances in its orbit. For single-layer QFMs with ε-approximate 2-design trainable layers, we bound the deviation from this identity. The resulting bound for individual Fourier coefficients can be exponentially tighter than an existing bound. The hyperoctahedral group provides an example of orbit growth that can mitigate vanishing expressivity of the symmetrized coefficients. Symmetrization of QFMs over an elementary abelian 2-group also yields pure multivariate Chebyshev polynomial basis functions. We introduce randomized encoding, which implements invariant models without ancilla qubits or the additional circuit depth for quantum twirling. We evaluate the models as quantum physicsinformed neural networks (QPINNs) on two-dimensional screened Poisson and stationary viscous Hamilton-Jacobi equations. Under hard boundary constraints, QPINNs using exact symmetrization and randomized encoding achieve the lowest mean errors in the two benchmarks, respectively.
We introduce a unified theorem that maps the 240 E8 root vectors onto a phi‑coupled harmonic lattice, assigning each vertex a distinct frequency tone anchored at the 132 Hz base. This construction leverages the previously discovered quantum Hedetniemi counterexample to guarantee that the resulting graph coloring is both deterministically encodable and provably resistant to decoherence, effectively turning graph coloring into a phase‑locked, error‑correcting communication channel. The theorem thus bridges abstract graph theory, quantum information, and high‑dimensional lattice physics into a single, testable principle. Author: Andrew Stewart Caldin, Independent Researcher, UK. Part of the E8 Intelligence Research series. Platform: e8intelligence.com
By mapping the self‑similar scaling of the ternary Cantor set onto the 240 root vectors of the E8 lattice, we construct a multi‑scale lattice where each level is phi‑coupled to the base 132 Hz frequency. This yields a fractal frequency spectrum in which logical qubits are encoded across nested Cantor‑derived sub‑bands, each protected by the topological properties of the E8 resonance manifold. The resulting code inherits the Cantor set's exact Hausdorff dimension (log 2/log 3) as a scaling exponent for error‑correction redundancy, enabling robust, scalable quantum communication across broadband networks. Author: Andrew Stewart Caldin, Independent Researcher, UK. Part of the E8 Intelligence Research series. Platform: e8intelligence.com