Robustness of statistical models

DOI10.1016/J.TOPOL.2023.108438MaRDI QIDQ6380100arXivFDO

Authors Andrea Loi, Stefano Matta

Publication date 12 October 2021

Published in arXiv

Full work available at URL https://doi.org/10.1016/J.TOPOL.2023.108438

Mathematics Subject Classification ID

Differential geometric aspects of statistical manifolds and information geometry (53B12) Connections (general theory) (53C05) Differential geometry of immersions (minimal, prescribed curvature, tight, etc.) (53C42) Implicit function theorems; global Newton methods on manifolds (58C15)

arXiv classification

math.STstat.TH

Abstract: A statistical structure $(g,T)$ on a smooth manifold $M$ induced by $(ildeM,ildeg,ildeT)$ is said to be {em robust} if there exists an open neighborhood of $(g,T)$ in the fine $C^{infty}$-topology consisting of statistical structures induced by $(ildeM,ildeg,ildeT)$. Using Nash--Gromov implicit function theorem, we show robustness of the generic statistical structure induced on $M$ by the standard linear statistical structure on $R^N$, for $N$ sufficiently large.

This page was built for publication: Robustness of statistical models

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6380100)