EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC-ND 4.0

Fixed-point analysis of weighted integrated gradients

Saidjon Kamolov

Annals of Mathematics and Computer Science · 20.03.2026 · 33

DOI: 10.56947/amcs.v33.792 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Annals of Mathematics and Computer Science, online erschienen am 20.03.2026. Verfasst von Saidjon Kamolov. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Feature attribution methods like Integrated Gradients (IG) are widely used to interpret deep neural networks. While typical extensions of IG introduce continuous weighting kernels along the integration path, these approaches are usually evaluated based on static axiomatic properties. We propose a theoretical framework analyzing Weighted Integrated Gradients (WIG) as a continuous mathematical operator acting on the model's function space. By investigating the sequence generated when iteratively applying the explanation to itself, we use Fixed-Point Theory and Taylor spectral decomposition to show that WIG functions as a spectral filter on model complexity. Our analysis identifies three regimes. First, standard IG acts as an identity operator, effectively functioning as an all-pass filter. Second, input-weighted explanations act as expansion operators or high-pass filters, amplifying higher-order non-linearities. Third, baseline-weighted explanations act as contraction mappings or low-pass filters. Iterative application of a baseline-weighted explanation operator converges to a linear surrogate, establishing a formal equivalence between baseline-weighted attribution and model distillation.

Zitieren

APA

Kamolov, S. (2026). Fixed-point analysis of weighted integrated gradients. Annals of Mathematics and Computer Science, 33. https://doi.org/10.56947/amcs.v33.792

Vancouver

Kamolov S. Fixed-point analysis of weighted integrated gradients. Annals of Mathematics and Computer Science. 2026;33. doi:10.56947/amcs.v33.792

BibTeX
@article{Kamolov2026,
  author = {Kamolov, Saidjon},
  title = {Fixed-point analysis of weighted integrated gradients},
  journal = {Annals of Mathematics and Computer Science},
  year = {2026},
  volume = {33},
  doi = {10.56947/amcs.v33.792}
}
Kostenlos starten →