New bounds for the empirical robust Kullback-Leibler divergence problem

DOI10.1016/j.ins.2023.118972OpenAlexW4366503330MaRDI QIDQ6124700

Ufuk Bahçeci

Publication date: 28 March 2024

Published in: Information Sciences (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1016/j.ins.2023.118972

zbMATH Keywords

robustKullback-Leibler divergencecompositeuniversal hypothesis testingLévy ball

Mathematics Subject Classification ID

Nonparametric hypothesis testing (62G10) Convex programming (90C25) Statistical aspects of information-theoretic topics (62B10)

Cites Work

• Unnamed Item
• Conic optimization via operator splitting and homogeneous self-dual embedding
• A test for population collinearity. A Kullback-Leibler information approach
• Randomized mixture models for probability density approximation and estimation
• On the tight constant in the multivariate Dvoretzky-Kiefer-Wolfowitz inequality
• CVXPY: A Python-Embedded Modeling Language for Convex Optimization
• Joint state and parameter robust estimation of stochastic nonlinear systems
• On universal hypotheses testing via large deviations
• Random coding strategies for minimum entropy
• On Choosing and Bounding Probability Metrics
• Asymptotically Optimal One- and Two-Sample Testing With Kernels
• Robust Kullback-Leibler Divergence and Universal Hypothesis Testing for Continuous Distributions
• Asymptotically Optimal Tests for Multinomial Distributions

This page was built for publication: New bounds for the empirical robust Kullback-Leibler divergence problem