English
Related papers

Related papers: Sandwiched R\'enyi Divergence Satisfies Data Proce…

200 papers

This paper characterizes convex information costs using an axiomatic approach. We employ mixture convexity and sub-additivity, which capture the idea that producing "balanced" outputs is less costly than producing ``extreme'' ones. Our…

Theoretical Economics · Economics 2025-09-03 Davide Bordoli , Ryota Iijima

Bounds on information combining are entropic inequalities that determine how the information, or entropy, of a set of random variables can change when they are combined in certain prescribed ways. Such bounds play an important role in…

Information Theory · Computer Science 2020-11-10 Christoph Hirche

Audenaert and Datta recently introduced a two-parameter family of relative R\'{e}nyi entropies, known as the $\alpha$-$z$-relative R\'{e}nyi entropies. The definition of the $\alpha$-$z$-relative R\'{e}nyi entropy unifies all previously…

Quantum Physics · Physics 2015-08-05 Mingyan Simon Lin , Marco Tomamichel

The conditional quantum mutual information $I(A;B|C)$ of a tripartite state $\rho_{ABC}$ is an information quantity which lies at the center of many problems in quantum information theory. Three of its main properties are that it is…

Quantum Physics · Physics 2015-03-17 Mario Berta , Kaushik P. Seshadreesan , Mark M. Wilde

Divergences are fundamental to the information criteria that underpin most signal processing algorithms. The alpha-beta family of divergences, designed for non-negative data, offers a versatile framework that parameterizes and continuously…

Machine Learning · Computer Science 2026-03-27 Sergio Cruces

This document focuses on translating various information-theoretic measures of distinguishability for probability distributions into measures of distin- guishability for quantum states. These measures should have important appli- cations in…

Quantum Physics · Physics 2007-05-23 Christopher A. Fuchs

The max-relative entropy and the conditional min-entropy it induces have become central to one-shot information theory. Both may be expressed in terms of a conic program over the positive semidefinite cone. Recently, it was shown that the…

Quantum Physics · Physics 2024-10-15 Ian George , Eric Chitambar

We provide a Sandwich Theorem (K\"onig (1972)) for positively homogeneous functionals that satisfy additivity only on a restricted domain. Our relaxation of additivity is based on a binary relation called convex-conic symmetric preorder,…

Functional Analysis · Mathematics 2023-04-07 Mario Ghossoub , Giulio Principi , Lorenzo Stanca

Recent research in the theory of overparametrized learning has sought to establish generalization guarantees in the interpolating regime. Such results have been established for a few common classes of methods, but so far not for ensemble…

Machine Learning · Statistics 2022-05-20 Yutong Wang , Clayton D. Scott

We show finite-size bounds on the deviation of the optimal type II error from its asymptotic value in the quantum hypothesis testing problem of Stein's lemma with composite null-hypothesis. The proof is based on some simple properties of a…

Quantum Physics · Physics 2014-07-07 Milán Mosonyi

The data processing inequality is central to information theory and motivates the study of monotonic divergences. However, it is not clear operationally we need to consider all such divergences. We establish a simple method for Pinsker…

Information Theory · Computer Science 2025-04-02 Ian George , Alice Zheng , Akshay Bansal

The presence of symmetries imposes a stringent set of constraints on a system. This constrained structure allows intelligent agents interacting with such a system to drastically improve the efficiency of learning and generalization, through…

Information Theory · Computer Science 2024-10-03 Hippolyte Charvin , Nicola Catenacci Volpi , Daniel Polani

We reduce the number of open additivity problems in quantum information theory by showing that four of them are equivalent. We show that the conjectures of additivity of the minimum output entropy of a quantum channel, additivity of the…

Quantum Physics · Physics 2009-11-10 Peter W. Shor

Top quark pairs produced at the Large Hadron Collider (LHC) provide a unique window into quantum information theory at high energies. One of the most ubiquitous measurements of quantum information is the violation of Bell's inequality. We…

High Energy Physics - Experiment · Physics 2022-02-24 Andrew Wildridge

A new sharp inequality featuring the differential R\'enyi entropy, the R\'enyi divergence and the R\'enyi cross-entropy of a pair of probability density functions is established. The equality is reached when one of the probability density…

Information Theory · Computer Science 2026-03-10 Razvan Gabriel Iagar , David Puertas-Centeno

Information theory provides tools to predict the performance of a learning algorithm on a given dataset. For instance, the accuracy of learning an unknown parameter can be upper bounded by reducing the learning task to hypothesis testing…

Quantum Physics · Physics 2026-04-21 Evan Peters

The concept of the smoothing parameter plays a crucial role in both lattice-based and code-based cryptography, primarily due to its effectiveness in achieving nearly uniform distributions through the addition of noise. Recent research by…

Information Theory · Computer Science 2024-05-17 Hao Yan , Cong Ling

In this paper, we first introduce and define several new information divergences in the space of transition matrices of finite Markov chains which measure the discrepancy between two Markov chains. These divergences offer natural…

Information Theory · Computer Science 2023-12-11 Youjia Wang , Michael C. H. Choi

The Holevo bound is a bound on the mutual information for a given quantum encoding. In 1996 Schumacher, Westmoreland and Wootters [Schumacher, Westmoreland and Wootters, Phys. Rev. Lett. 76, 3452 (1996)] derived a bound which reduces to the…

Quantum Physics · Physics 2015-06-26 Kurt Jacobs

We investigate the cutoff phenomenon for Markov processes under information divergences such as $f$-divergences and R\'enyi divergences. We classify most common divergences into four types, namely $L^2$-type, $\mathrm{TV}$-type,…

Probability · Mathematics 2025-01-23 Youjia Wang , Michael C. H. Choi