EUVIMEDEUVIMED entdecken
Crossref

Geometrically Inspired Kernel Machines for Collaborative Learning Beyond Gradient Descent (Abstract Reprint)

Mohit Kumar, Alexander Valentinitsch, Magdalena Fuchs, Mathias Brucker, Juliana Bowles, Adnan Husakovic, Ali Abbas, Bernhard A. Moser

Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (47) · 39871-39871

DOI: 10.1609/aaai.v40i47.41386 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Mohit Kumar und 7 weiteren Autor:innen.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

This paper develops a novel mathematical framework for collaborative learning by means of geometrically inspired kernel machines which includes statements on the bounds of generalisation and approximation errors, and sample complexity. For classification problems, this approach allows us to learn bounded geometric structures around given data points and hence solve the global model learning problem in an efficient way by exploiting convexity properties of the related optimisation problem in a Reproducing Kernel Hilbert Space (RKHS). In this way, we can reduce classification problems to determining the closest bounded geometric structure from a given data point. Further advantages that come with our solution is that our approach does not require clients to perform multiple epochs of local optimisation using stochastic gradient descent, nor require rounds of communication between client/server for optimising the global model. We highlight that numerous experiments have shown that the proposed method is a competitive alternative to the state-of-the-art.

Zitieren

APA

Kumar, M., Valentinitsch, A., Fuchs, M., Brucker, M., Bowles, J., Husakovic, A., Abbas, A., & Moser, B. A. (2026). Geometrically Inspired Kernel Machines for Collaborative Learning Beyond Gradient Descent (Abstract Reprint). Proceedings of the AAAI Conference on Artificial Intelligence, 40(47), 39871-39871. https://doi.org/10.1609/aaai.v40i47.41386

Vancouver

Kumar M, Valentinitsch A, Fuchs M, Brucker M, Bowles J, Husakovic A, et al. Geometrically Inspired Kernel Machines for Collaborative Learning Beyond Gradient Descent (Abstract Reprint). Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(47):39871-39871. doi:10.1609/aaai.v40i47.41386

BibTeX
@article{Kumar2026,
  author = {Kumar, Mohit and Valentinitsch, Alexander and Fuchs, Magdalena and Brucker, Mathias and Bowles, Juliana and Husakovic, Adnan and Abbas, Ali and Moser, Bernhard A.},
  title = {Geometrically Inspired Kernel Machines for Collaborative Learning Beyond Gradient Descent (Abstract Reprint)},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2026},
  volume = {40},
  number = {47},
  pages = {39871--39871},
  doi = {10.1609/aaai.v40i47.41386}
}
Kostenlos starten →