5 citations · 13 across the 10 of their papers we have counts for
7 papers · 1 filter
The Information Bottleneck is NP-hard
Roberto Bruno, Ugo Vaccaro
Given a joint distribution on a finite alphabet, the information bottleneck method seeks a representation of that is as informative as possible about while com…
Wyner's Common Information and the Common Entropy are NP-Hard to Compute
Roberto Bruno, Ugo Vaccaro
Wyner's common information and the common entropy of a pair of random variables with finite ranges and joint distribution are both defined by an optimizat…
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…
Constrained Maximum Entropy Contiguous Aggregations
Roberto Bruno, Ugo Vaccaro
Given a probability distribution and an integer , a contiguous aggregation of is a probability distribution such…
An Information Theoretic Treatment of Yager's Probability Distribution Negation
Roberto Bruno, Ugo Vaccaro
In the seminal paper (Yager 2015), Yager defined the negation of a probability distribution , as the distribution $\overline{\mathbf{p}} = (\overline{p}…
The Sharma-Mittal Entropy is Subadditive and Supermodular on the Majorization Lattice
Roberto Bruno, Ugo Vaccaro
We prove that Sharma-Mittal entropy is a subadditive and supermodular function on the lattice of all -dimensional probability distributions, ordered according to the partial ord…
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"…