-Divergence Inequalities

I Sason, S Verdú - IEEE Transactions on Information Theory, 2016 - ieeexplore.ieee.org
This paper develops systematic approaches to obtain f-divergence inequalities, dealing with
pairs of probability measures defined on arbitrary alphabets. Functional domination is one …

Quantum differential privacy: An information theory perspective

C Hirche, C Rouzé, DS França - IEEE Transactions on …, 2023 - ieeexplore.ieee.org
Differential privacy has been an exceptionally successful concept when it comes to
providing provable security guarantees for classical computations. More recently, the …

Wiretap channels: Nonasymptotic fundamental limits

W Yang, RF Schaefer, HV Poor - IEEE Transactions on …, 2019 - ieeexplore.ieee.org
This paper investigates the maximal secret communication rate over a wiretap channel
subject to reliability and secrecy constraints at a given blocklength. New achievability and …

Strong functional representation lemma and applications to coding theorems

CT Li, A El Gamal - IEEE Transactions on Information Theory, 2018 - ieeexplore.ieee.org
This paper shows that for any random variables X and Y, it is possible to represent Y as a
function of (X, Z) such that Z is independent of X and I (X; Z| Y)≤ log (I (X; Y)+ 1)+ 4 bits. We …

Smoothing of binary codes, uniform distributions, and applications

M Pathegama, A Barg - Entropy, 2023 - mdpi.com
The action of a noise operator on a code transforms it into a distribution on the respective
space. Some common examples from information theory include Bernoulli noise acting on a …

On f-Divergences: Integral Representations, Local Behavior, and Inequalities

I Sason - Entropy, 2018 - mdpi.com
This paper is focused on f-divergences, consisting of three main contributions. The first one
introduces integral representations of a general f-divergence by means of the relative …

Finite-blocklength bounds for wiretap channels

W Yang, RF Schaefer, HV Poor - 2016 IEEE International …, 2016 - ieeexplore.ieee.org
This paper investigates the maximal secrecy rate over a wiretap channel subject to reliability
and secrecy constraints at a given blocklength. New achievability and converse bounds are …

To split or not to split: The impact of disparate treatment in classification

H Wang, H Hsu, M Diaz… - IEEE Transactions on …, 2021 - ieeexplore.ieee.org
Disparate treatment occurs when a machine learning model produces different decisions for
individuals based on a legally protected or sensitive attribute (eg, age, sex). In domains …

Error exponent and strong converse for quantum soft covering

HC Cheng, L Gao - IEEE Transactions on Information Theory, 2023 - ieeexplore.ieee.org
How well can we approximate a quantum channel output state using a random codebook
with a certain size? In this work, we study the quantum soft covering problem, which uses a …

The sample complexity of approximate rejection sampling with applications to smoothed online learning

A Block, Y Polyanskiy - The Thirty Sixth Annual Conference …, 2023 - proceedings.mlr.press
Suppose we are given access to $ n $ independent samples from distribution $\mu $ and we
wish to output one of them with the goal of making the outputdistributed as close as possible …