Bounds on f-Divergences between Distributions within Generalized Quasi-$\varepsilon$-Neighborhood

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Yu, Xinchun, Wei, Shuangqing, Zhang, Xiao-Ping
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909729757855744
author Yu, Xinchun
Wei, Shuangqing
Zhang, Xiao-Ping
author_facet Yu, Xinchun
Wei, Shuangqing
Zhang, Xiao-Ping
contents This work establishes computable bounds between f-divergences for probability measures within a generalized quasi-$\varepsilon_{(M,m)}$-neighborhood framework. We make the following key contributions. (1) a unified characterization of local distributional proximity beyond structural constraints is provided, which encompasses discrete/continuous cases through parametric flexibility. (2) First-order differentiable $f$-divergence classification with Taylor-based inequalities is established, which generalizes $χ^2$-divergence results to broader function classes. (3) We provide tighter reverse Pinsker's inequalities than existing ones, bridging asymptotic analysis and computable bounds. The proposed framework demonstrates particular efficacy in goodness-of-fit test asymptotics while maintaining computational tractability.
format Preprint
id arxiv_https___arxiv_org_abs_2406_00939
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Bounds on f-Divergences between Distributions within Generalized Quasi-$\varepsilon$-Neighborhood
Yu, Xinchun
Wei, Shuangqing
Zhang, Xiao-Ping
Information Theory
This work establishes computable bounds between f-divergences for probability measures within a generalized quasi-$\varepsilon_{(M,m)}$-neighborhood framework. We make the following key contributions. (1) a unified characterization of local distributional proximity beyond structural constraints is provided, which encompasses discrete/continuous cases through parametric flexibility. (2) First-order differentiable $f$-divergence classification with Taylor-based inequalities is established, which generalizes $χ^2$-divergence results to broader function classes. (3) We provide tighter reverse Pinsker's inequalities than existing ones, bridging asymptotic analysis and computable bounds. The proposed framework demonstrates particular efficacy in goodness-of-fit test asymptotics while maintaining computational tractability.
title Bounds on f-Divergences between Distributions within Generalized Quasi-$\varepsilon$-Neighborhood
topic Information Theory
url https://arxiv.org/abs/2406.00939