EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Differentiable learning of sparse lossless Fourier filters

Mohammed Terry-Jack, Simon O’Keefe

AIP Advances · 01.07.2026 · 16 (7)

DOI: 10.1063/5.0324352 ↗

Kurz gefasst

Fachartikel in der Zeitschrift AIP Advances, online erschienen am 16.07.2026. Verfasst von Mohammed Terry-Jack und 1 weiteren Autor:innen. Die Arbeit nennt 21 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Purpose

The Fourier transform-bounded Kolmogorov complexity proposed in the study by Terry-Jack [J. Software Eng. Appl. 15(10), 359 (2022)], as well as in that by Terry-Jack and O’Keefe [Physica D 453, 133824 (2023)], relies on finding the minimal subset of frequency coefficients that can exactly reconstruct the original image. However, we show that finding this minimal subset of coefficients is a combinatorial optimization problem that becomes computationally intractable for large images. As such, naive solutions such as greedy search are impractical at scale, limiting the feasibility and application of Fourier transform bounded Kolmogorov complexity.

Methods

We reformulate the hard combinatorial problem as a differentiable optimization task via the introduction of smooth surrogates for non-differentiable components such as the quantization step and use a straight-through estimator (STE) to learn sparse binary masks (frequency filters) that allow for exact reconstruction of the original image via gradient-descent.

Results

Experiments on elementary cellular automata, QR codes, a natural binary image, and random noise demonstrate that sparse Fourier masks capable of bit-exact reconstruction can be learned efficiently at scales that are impractical for a combinatorial or greedy search. Although the problem admits a linear LASSO reformulation that enables classical sparse-recovery methods, experiments against a FISTA baseline demonstrate the advantages of directly optimizing the original nonlinear objective via an STE.

Conclusion

This work provides the first practical framework for learning lossless Fourier-domain filters at scale by reframing a hard combinatorial problem as a differentiable learning task.

Zitieren

APA

Terry-Jack, M., & O’Keefe, S. (2026). Differentiable learning of sparse lossless Fourier filters. AIP Advances, 16(7). https://doi.org/10.1063/5.0324352

Vancouver

Terry-Jack M, O’Keefe S. Differentiable learning of sparse lossless Fourier filters. AIP Advances. 2026;16(7). doi:10.1063/5.0324352

BibTeX
@article{TerryJack2026,
  author = {Terry-Jack, Mohammed and O’Keefe, Simon},
  title = {Differentiable learning of sparse lossless Fourier filters},
  journal = {AIP Advances},
  year = {2026},
  volume = {16},
  number = {7},
  doi = {10.1063/5.0324352}
}
Kostenlos starten →