EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

An Approach to Fisher-Rao Metric for Infinite Dimensional Non-Parametric Information Geometry

Bing Cheng iD, Howell Tong

Entropy · 25.03.2026 · 28 (4) · 374

DOI: 10.3390/e28040374 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Entropy, online erschienen am 25.03.2026. Verfasst von Bing Cheng und 1 weiteren Autor:innen. Beteiligte Einrichtung: Academy of Mathematics and Systems Science, Chinese Academy of Sciences, Beijing 100190, China. Die Arbeit nennt 12 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Non-parametric information geometry has long faced an “intractability barrier”: in the infinite-dimensional setting, the Fisher–Rao metric is a weak Riemannian metric functional that lacks a bounded inverse, rendering classical optimization and estimation techniques computationally inaccessible. This paper resolves this barrier by building the statistical manifold on the Orlicz space L0Φ(Pf) (the Pistone–Sempi manifold), which provides the necessary exponential integrability for score functions and a rigorous Fréchet differentiability for the Kullback–Leibler divergence. We introduce a novel Structural Decomposition of the Tangent Space (TfM=S⊕S⊥), where the infinite-dimensional space is split into a finite-dimensional covariate subspace (S)—representing the observable system—and its orthogonal complement (S⊥). Through this decomposition, we derive the Covariate Fisher Information Matrix (cFIM), denoted as Gf, which acts as the computable “Hilbertian slice” of the otherwise intractable metric functional. Key theoretical contributions include proving the Trace Theorem (HG(f)=Tr(Gf)) to identify G-entropy as a fundamental geometric invariant; demonstrating the Geometric Invariance of the Covariate Fisher Information Matrix (cFIM) as a covariant (0,2)-tensor under reparameterization; establishing the cFIM as the local Hessian of the KL-divergence; and characterizing the Efficiency Standard through a generalized Cramer–Rao Lower Bound for semi-parametric inference within the Orlicz manifold. Furthermore, we demonstrate that this framework provides a formal mathematical justification for the Manifold Hypothesis, as the structural decomposition naturally identifies the low-dimensional subspace where information is concentrated. By shifting the focus from the intractable global manifold to the tractable covariate geometry, this framework proves that statistical information is not a property of data alone, but an active geometric interaction between the environment (data), the system (covariate subspace), and the mechanism (Fisher–Rao connection).

Schlagwörter

Stichwörter der Autor:innen

Cramer–Rao Lower BoundFishe-r-Rao metricG-entropyKullback–Leibler divergenceStein scoreinformation geometrymanifold hypothesisnon-parametricorthogonal decompositiontangent space

Autor:innen und Institutionen

  • Academy of Mathematics and Systems Science, Chinese Academy of Sciences, Beijing 100190, China.
  • Department of Statistics, London School of Economics and Political Science, London WC2A 2AE, UK.
  • Department of Statistics and Data Science, Tsinghua University, Beijing 100084, China.
  • Paula and Gregory Chow Institute for the Studies in Economics, Xiamen University, Xiamen 361005, China.

ORCID-Profile: Bing Cheng

Zitieren

APA

Cheng, B., & Tong, H. (2026). An Approach to Fisher-Rao Metric for Infinite Dimensional Non-Parametric Information Geometry. Entropy, 28(4), 374. https://doi.org/10.3390/e28040374

Vancouver

Cheng B, Tong H. An Approach to Fisher-Rao Metric for Infinite Dimensional Non-Parametric Information Geometry. Entropy. 2026;28(4):374. doi:10.3390/e28040374

BibTeX
@article{Cheng2026,
  author = {Cheng, Bing and Tong, Howell},
  title = {An Approach to Fisher-Rao Metric for Infinite Dimensional Non-Parametric Information Geometry},
  journal = {Entropy},
  year = {2026},
  volume = {28},
  number = {4},
  pages = {374},
  doi = {10.3390/e28040374}
}
Kostenlos starten →