Asymptotics for Frequency Redundancies in Quantum Machine Learning Models
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 favours low frequencies, highlighting the importance of well-thought-out encoding strategies when constructing a QFM.
Related
- Compact and stable representation of real-frequency spectral functions for machine learning
- When Quantum Meets AI: Quantum Methods for Machine Learning and Machine Learning Methods for Quantum Systems
- Application a quantum machine learning algorithm to the applied problem of modeling the thermal regime of a servers
- Photonic Time-Delayed Quantum Extreme Learning Machine
- Machine learning quantum data to accelerate quantum Monte Carlo
BibTeX
@misc{paul2026asymptotics,
title = {{Asymptotics for Frequency Redundancies in Quantum Machine Learning Models}},
author = {Felix Paul and Bhilahari Jeevanesan and Peter Jung},
howpublished = {arXiv},
year = {2026},
month = sep,
doi = {10.48550/arxiv.2609.21916},
eprint = {2609.21916},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2609.21916},
}
RIS
TY - UNPB
TI - Asymptotics for Frequency Redundancies in Quantum Machine Learning Models
AU - Felix Paul
AU - Bhilahari Jeevanesan
AU - Peter Jung
PY - 2026
DA - 2026/09/18
PB - arXiv
DO - 10.48550/arxiv.2609.21916
UR - https://arxiv.org/abs/2609.21916
AB - 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.
ER -