Robustness of statistical models

10/12/2021
by   Andrea Loi, et al.
0

A statistical structure (g, T) on a smooth manifold M induced by (M̃, g̃, T̃) is said to be robust if there exists an open neighborhood of (g,T) in the fine C^∞-topology consisting of statistical structures induced by (M̃, g̃, T̃). Using Nash–Gromov implicit function theorem, we show robustness of the generic statistical structure induced on M by the standard linear statistical structure on ^N, for N sufficiently large.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
05/08/2023

The induced two paths problem

We give an approximate Menger-type theorem for when a graph G contains t...
research
08/03/2023

Greedy Matroid Algorithm And Computational Persistent Homology

An important problem in computational topology is to calculate the homol...
research
10/13/2022

RWN: A Novel Neighborhood-Based Method for Statistical Disclosure Control

A novel variation of the data swapping approach to statistical disclosur...
research
02/18/2020

Foundations of Structural Statistics: Statistical Manifolds

Upon a consistent topological statistical theory the application of stru...
research
03/02/2020

PSF–NET: A Non-parametric Point Spread Function Model for Ground Based Optical Telescopes

Ground based optical telescopes are seriously affected by atmospheric tu...
research
06/10/2022

Fisher SAM: Information Geometry and Sharpness Aware Minimisation

Recent sharpness-aware minimisation (SAM) is known to find flat minima w...
research
05/19/2019

What Do Adversarially Robust Models Look At?

In this paper, we address the open question: "What do adversarially robu...

Please sign up or login with your details

Forgot password? Click here to reset