14 citations · 27 across the 17 of their papers we have counts for
9 papers · 1 filter
A One-Sided McDiarmid-Type Inequality for Heavy Tails via Reverse KL Tensorization
Hanuka Eshima, Amedeo Roberto Esposito, Andrea Paudice
We revisit McDiarmid's inequality, a central tool in statistical learning theory and algorithm analysis. We show that large deviations above the mean are exponentially unlikely for…
Distribution-Dependent Improvements of McDiarmid's Inequality via Rényi Divergence
Amedeo Roberto Esposito, Adrien Vandenbroucque, Michael Gastpar
We investigate whether Rényi divergence can sharpen McDiarmid's inequality and its distribution-dependent refinement induced by KL divergence. Starting from Marton's transportation…
Beyond Hypercontractivity: Stronger Communication Converses via Rényi Contraction
Ryo Hommura Moore, Amedeo Roberto Esposito
We study the relationship between strong data-processing inequalities for Rényi divergences and hypercontractivity. For Rényi divergences of order greater than one, we characterize…
On the Impossibility of Estimating the Average Mixing Time
Nathan A. Judd, Amedeo Roberto Esposito
We establish nearly-matching converse bounds on the sample complexity of estimating the average mixing time of a Markov chain from a single stationary trajectory. Unlike the worst-…
Finite-Sample Binary Hypothesis Testing via Rényi Divergences: Strong Converse and Local Privacy
Roberto Bruno, Adrien Vandenbroucque, Amedeo Roberto Esposito
We study asymmetric simple binary hypothesis testing between and , based on independent and identically distributed observations. Leveraging a variat…
Finite Sample Bounds for Composite Hypothesis Testing
Elías Vera-Sigüenza, Amedeo Roberto Esposito
We investigate composite binary hypothesis testing in the finite sample regime under asymmetric error constraints. Using Rényi divergences, we derive explicit achievability and con…
Minimax Quantile Bounds via Information Measures
Amedeo Roberto Esposito
We develop a unified information-theoretic framework for lower bounding minimax quantiles. The starting point is a loss-adapted Neyman--Pearson metaconverse that bounds the minimax…
A Finite-Sample Strong Converse for Binary Hypothesis Testing via (Reverse) Rényi Divergence
Roberto Bruno, Adrien Vandenbroucque, Amedeo Roberto Esposito
This work investigates binary hypothesis testing between and in the finite-sample regime under asymmetric error constraints. By employing the ``reverse"…
Contraction of Rényi Divergences for Discrete Channels: Properties and Applications
Adrien Vandenbroucque, Amedeo Roberto Esposito, Michael Gastpar
This work explores properties of Strong Data-Processing constants for Rényi Divergences. Parallels are made with the well-studied -Divergences, and it is shown that the order $α…