Skip to content
AI News HubLIVE
Original source2 min read

JA-SIREN: Deterministic Initialization for Sinusoidal Networks via Spectral Matching

Summary

JA-SIREN introduces a deterministic initialization scheme for sinusoidal networks based on classical spectral analysis, using the Discrete Sine Transform and Jacobi-Anger expansion to derive closed-form weights for a two-layer sinusoidal MLP. On the Kodak dataset, it achieves a mean PSNR of 67.18 dB, a 21.30 dB improvement over the best baseline, with zero run-to-run variance, addressing the inconsistency of stochastic initialization in implicit neural representations.

SourcearXiv Computer VisionAuthor: Mohammed Alsakabi, Kejia Hu, John M. Dolan, Ozan K. Tonguz
JA-SIREN: Deterministic Initialization for Sinusoidal Networks via Spectral Matching
Report an error

The correction channel is not available yet. You can copy the article reference below for later.

Correction instructions
Read article

[2606.06671] JA-SIREN: Deterministic Initialization for Sinusoidal Networks via Spectral Matching

[Submitted on 4 Jun 2026]

Title:JA-SIREN: Deterministic Initialization for Sinusoidal Networks via Spectral Matching

View a PDF of the paper titled JA-SIREN: Deterministic Initialization for Sinusoidal Networks via Spectral Matching, by Mohammed Alsakabi and 3 other authors

View PDF HTML (experimental)

Abstract:Existing implicit neural representation (INR) approaches suffer from stochastic initialization that does not guarantee consistent or high-quality performance across runs, with variations reaching more than 2.5 dB (78%) in image regression. This variation is problematic for scientific computing and simulation, where result reproducibility is crucial. To address this problem, we present Jacobi-Anger Sinusoidal Representation Network (JA-SIREN), a deterministic initialization scheme for sinusoidal networks grounded in classical spectral analysis. By computing the Discrete Sine Transform (DST) of the target signal and leveraging the Jacobi-Anger expansion, we derive closed-form weights for a two-layer sinusoidal MLP that analytically match the network's initial spectral response to the target signal, requiring no random seed or additional hyperparameter tuning. On the Kodak dataset, JA-SIREN achieves a mean PSNR of 67.18 dB, a 21.30 dB improvement over the best baseline. This is achieved with zero run-to-run variance, confirming that spectrally-informed initialization is a more effective and reproducible alternative to stochastic initialization for sinusoidal INRs.

Subjects:

Computer Vision and Pattern Recognition (cs.CV)

Cite as: arXiv:2606.06671 [cs.CV]

(or arXiv:2606.06671v1 [cs.CV] for this version)

https://doi.org/10.48550/arXiv.2606.06671

arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Mohammed Alsakabi [view email] [v1] Thu, 4 Jun 2026 19:45:43 UTC (2,952 KB)

Full-text links:

Access Paper:

View a PDF of the paper titled JA-SIREN: Deterministic Initialization for Sinusoidal Networks via Spectral Matching, by Mohammed Alsakabi and 3 other authors

View PDF

HTML (experimental)

TeX Source

view license

Current browse context:

cs.CV

new | recent | 2026-06

Change to browse by:

cs

References & Citations

NASA ADS

Google Scholar

Semantic Scholar

Loading...

Data provided by:

Bibliographic Tools

Bibliographic and Citation Tools

Bibliographic Explorer Toggle

Bibliographic Explorer (What is the Explorer?)

Connected Papers Toggle

Connected Papers (What is Connected Papers?)

Litmaps Toggle

Litmaps (What is Litmaps?)

scite.ai Toggle

scite Smart Citations (What are Smart Citations?)

Code, Data, Media

Code, Data and Media Associated with this Article

alphaXiv Toggle

alphaXiv (What is alphaXiv?)

Links to Code Toggle

CatalyzeX Code Finder for Papers (What is CatalyzeX?)

DagsHub Toggle

DagsHub (What is DagsHub?)

GotitPub Toggle

Gotit.pub (What is GotitPub?)

Huggingface Toggle

Hugging Face (What is Huggingface?)

ScienceCast Toggle

ScienceCast (What is ScienceCast?)

Demos

Demos

Replicate Toggle

Replicate (What is Replicate?)

Spaces Toggle

Hugging Face Spaces (What is Spaces?)

Spaces Toggle

TXYZ.AI (What is TXYZ.AI?)

Related Papers

Recommenders and Search Tools

Link to Influence Flower

Influence Flower (What are Influence Flowers?)

Core recommender toggle

CORE Recommender (What is CORE?)

Author

Venue

Institution

Topic

About arXivLabs

arXivLabs: experimental projects with community collaborators

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.

Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)

Key points and analysis

Article intelligence

ResearchersAdvanced

Key points

  • Derives closed-form weights for a two-layer sinusoidal MLP by computing the Discrete Sine Transform of the target signal and leveraging the Jacobi-Anger expansion, requiring no random seed or hyperparameter tuning.
  • Achieves a mean PSNR of 67.18 dB on the Kodak dataset, a 21.30 dB improvement over the best baseline, with zero run-to-run variance.
  • Deterministic initialization ensures reproducibility crucial for scientific computing and simulation.

Highlights and analysis are generated automatically and may contain errors. Check the original source.