Skip to content
AI News HubLIVE
Original source2 min read

Fisher Width: A Geometric Measure of Complexity on Statistical Manifolds

Summary

The paper introduces Fisher width, a Fisher-geometric analogue of Gaussian width for statistical manifolds, develops its basic theory, proves a generalization bound for Fisher-Lipschitz hypothesis classes, and proposes computable estimators evaluated on MNIST.

SourcearXiv Machine LearningAuthor: Vu Khac Ky
Fisher Width: A Geometric Measure of Complexity on Statistical Manifolds
Report an error

The correction channel is not available yet. You can copy the article reference below for later.

Correction instructions
Read article

[2606.18306] Fisher Width: A Geometric Measure of Complexity on Statistical Manifolds

[Submitted on 16 Jun 2026]

Title:Fisher Width: A Geometric Measure of Complexity on Statistical Manifolds

View a PDF of the paper titled Fisher Width: A Geometric Measure of Complexity on Statistical Manifolds, by Vu Khac Ky

View PDF HTML (experimental)

Abstract:Gaussian width is a central geometric complexity measure in high-dimensional probability, compressed sensing, convex optimization, and learning theory. It quantifies the average extent of a set along random directions, thereby capturing the effective dimension of constraint sets, hypothesis classes, and descent cones. However, this notion is intrinsically Euclidean. Statistical models instead carry a natural Riemannian geometry induced by the Fisher information metric, where directions are scaled according to statistical distinguishability rather than ambient Euclidean length.

We introduce Fisher width, a Fisher-geometric analogue of Gaussian width for statistical manifolds. At a parameter point $\theta$, Fisher width replaces the Euclidean identity by the local metric tensor $G(\theta)^{1/2}$, measuring the Gaussian width of the Fisher-rescaled set. This makes the resulting quantity sensitive to local statistical curvature and invariant under smooth reparameterizations.

We develop the basic theory of Fisher width, showing that it retains key structural features of Gaussian width, including concentration, metric perturbation stability, and spectral comparison bounds with the Euclidean baseline, while also capturing anisotropic geometric effects invisible to Euclidean measures. As an application, we prove a generalization bound for Fisher-Lipschitz hypothesis classes and propose computable estimators, which we evaluate empirically on MNIST across three model classes.

Fisher width is to statistical manifolds what Gaussian width is to Euclidean convex bodies. This work lays the foundation for studying complexity and learning on curved statistical manifolds.

Comments: 48 pages, 3 figures

Subjects:

Machine Learning (cs.LG); Machine Learning (stat.ML)

MSC classes: 62R10, 60G15, 68T05

Cite as: arXiv:2606.18306 [cs.LG]

(or arXiv:2606.18306v1 [cs.LG] for this version)

https://doi.org/10.48550/arXiv.2606.18306

arXiv-issued DOI via DataCite

Submission history

From: Ky Vu Khac [view email] [v1] Tue, 16 Jun 2026 07:04:47 UTC (277 KB)

Full-text links:

Access Paper:

View a PDF of the paper titled Fisher Width: A Geometric Measure of Complexity on Statistical Manifolds, by Vu Khac Ky

View PDF

HTML (experimental)

TeX Source

view license

Current browse context:

cs.LG

new | recent | 2026-06

Change to browse by:

cs stat stat.ML

References & Citations

NASA ADS

Google Scholar

Semantic Scholar

Loading...

Data provided by:

Bibliographic Tools

Bibliographic and Citation Tools

Bibliographic Explorer Toggle

Bibliographic Explorer (What is the Explorer?)

Connected Papers Toggle

Connected Papers (What is Connected Papers?)

Litmaps Toggle

Litmaps (What is Litmaps?)

scite.ai Toggle

scite Smart Citations (What are Smart Citations?)

Code, Data, Media

Code, Data and Media Associated with this Article

alphaXiv Toggle

alphaXiv (What is alphaXiv?)

Links to Code Toggle

CatalyzeX Code Finder for Papers (What is CatalyzeX?)

DagsHub Toggle

DagsHub (What is DagsHub?)

GotitPub Toggle

Gotit.pub (What is GotitPub?)

Huggingface Toggle

Hugging Face (What is Huggingface?)

ScienceCast Toggle

ScienceCast (What is ScienceCast?)

Demos

Demos

Replicate Toggle

Replicate (What is Replicate?)

Spaces Toggle

Hugging Face Spaces (What is Spaces?)

Spaces Toggle

TXYZ.AI (What is TXYZ.AI?)

Related Papers

Recommenders and Search Tools

Link to Influence Flower

Influence Flower (What are Influence Flowers?)

Core recommender toggle

CORE Recommender (What is CORE?)

IArxiv recommender toggle

IArxiv Recommender (What is IArxiv?)

Author

Venue

Institution

Topic

About arXivLabs

arXivLabs: experimental projects with community collaborators

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.

Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)

Key points and analysis

Article intelligence

ResearchersAdvanced

Key points

  • Fisher width replaces the Euclidean identity with the local metric tensor G(θ)^{1/2} to measure the Gaussian width of a Fisher-rescaled set at parameter point θ.
  • It is sensitive to local statistical curvature and invariant under smooth reparameterizations, capturing anisotropic geometric effects invisible to Euclidean measures.
  • The theory retains key features of Gaussian width, including concentration, metric perturbation stability, and spectral comparison bounds with the Euclidean baseline.
  • Applications include a generalization bound for Fisher-Lipschitz hypothesis classes and computable estimators evaluated empirically on MNIST across three model classes.

Highlights and analysis are generated automatically and may contain errors. Check the original source.