EUVIMEDEUVIMED entdecken
Crossref

Normalized Maximum Likelihood Code-Length on Riemannian Data Spaces

Kota Fukuzawa, Atsushi Suzuki, Kenji Yamanishi

IEEE Transactions on Information Theory · 2026-07 · 72 (7) · 5059-5076

DOI: 10.1109/tit.2026.3690992 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Information Theory, 2026-07. Verfasst von Kota Fukuzawa und 2 weiteren Autor:innen. Gefördert von: Japan Society for the Promotion of Science (JSPS) KAKENHI.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

In recent years, with the large-scale expansion of graph data, there has been an increased focus on Riemannian data spaces other than Euclidean space. In particular, the development of hyperbolic spaces has been remarkable, and they have high expressive power for graph data with hierarchical structures. Normalized Maximum Likelihood (NML) is employed in regret minimization and model selection. However, existing formulations of NML have been developed primarily in Euclidean spaces and are inherently dependent on the choice of coordinate systems, making it non-trivial to extend NML to Riemannian manifolds. In this study, we define a new NML that reflects the geometric structure of Riemannian manifolds, called the Riemannian manifold NML (Rm-NML). This Rm-NML is invariant under coordinate transformations and coincides with the conventional NML under the natural parameterization in Euclidean space. We extend existing computational techniques for NML to the setting of Riemannian manifolds. Furthermore, we derive a method to simplify the computation of Rm-NML on Riemannian symmetric spaces, which encompass data spaces of growing interest such as hyperbolic spaces. To illustrate the practical application of our proposed method, we explicitly computed the Rm-NML for normal distributions on hyperbolic spaces.

Förderung

  • Japan Society for the Promotion of Science (JSPS) KAKENHI

Zitieren

APA

Fukuzawa, K., Suzuki, A., & Yamanishi, K. (2026). Normalized Maximum Likelihood Code-Length on Riemannian Data Spaces. IEEE Transactions on Information Theory, 72(7), 5059-5076. https://doi.org/10.1109/tit.2026.3690992

Vancouver

Fukuzawa K, Suzuki A, Yamanishi K. Normalized Maximum Likelihood Code-Length on Riemannian Data Spaces. IEEE Transactions on Information Theory. 2026;72(7):5059-5076. doi:10.1109/tit.2026.3690992

BibTeX
@article{Fukuzawa2026,
  author = {Fukuzawa, Kota and Suzuki, Atsushi and Yamanishi, Kenji},
  title = {Normalized Maximum Likelihood Code-Length on Riemannian Data Spaces},
  journal = {IEEE Transactions on Information Theory},
  year = {2026},
  volume = {72},
  number = {7},
  pages = {5059--5076},
  doi = {10.1109/tit.2026.3690992}
}
Kostenlos starten →