EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

FAdamWav: A Fractional Wavelet Gradient Optimizer for Neural Networks

Oscar Herrera-Alcántara, Salvador Arellano-Balderas, Sandra Rodríguez-Mondragón, José Alejandro Reyes-Ortíz, Jaime Navarro-Fuentes

Fractal and Fractional · 26.02.2026 · 10 (3) · 149

DOI: 10.3390/fractalfract10030149 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Fractal and Fractional, online erschienen am 26.02.2026. Verfasst von Oscar Herrera-Alcántara und 4 weiteren Autor:innen. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 38 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The optimizer is a critical element of neural networks because it computes their optimal parameters through a training process. The Adam optimizer is considered the state of the art in deep learning. However, a drawback is the cost of storing and computing their gradients. A useful tool for addressing this issue is the application of the wavelet transform, and other relevant tool is the fractional derivative, which can be used to create fractional gradient optimizers. This research combines the wavelet transform and fractional optimizers to propose FAdamWav, a fractional version of Adam that uses (i) a parametric discrete wavelet transform to theoretically save 50%, 75% or 87.5% of gradient’s memory with one, two or three transformation levels, and (ii) a fractional gradient to optimize the neural network parameters. Experiments indicate that the saved memory is lower than the theoretical bounds, but memory is saved and fractional wavelet-based optimizers have competitive performance compared to their non-fractional and non-wavelet counterparts.

Zitieren

APA

Herrera-Alcántara, O., Arellano-Balderas, S., Rodríguez-Mondragón, S., Reyes-Ortíz, J. A., & Navarro-Fuentes, J. (2026). FAdamWav: A Fractional Wavelet Gradient Optimizer for Neural Networks. Fractal and Fractional, 10(3), 149. https://doi.org/10.3390/fractalfract10030149

Vancouver

Herrera-Alcántara O, Arellano-Balderas S, Rodríguez-Mondragón S, Reyes-Ortíz JA, Navarro-Fuentes J. FAdamWav: A Fractional Wavelet Gradient Optimizer for Neural Networks. Fractal and Fractional. 2026;10(3):149. doi:10.3390/fractalfract10030149

BibTeX
@article{HerreraAlcntara2026,
  author = {Herrera-Alcántara, Oscar and Arellano-Balderas, Salvador and Rodríguez-Mondragón, Sandra and Reyes-Ortíz, José Alejandro and Navarro-Fuentes, Jaime},
  title = {FAdamWav: A Fractional Wavelet Gradient Optimizer for Neural Networks},
  journal = {Fractal and Fractional},
  year = {2026},
  volume = {10},
  number = {3},
  pages = {149},
  doi = {10.3390/fractalfract10030149}
}
Kostenlos starten →