English
Related papers

Related papers: $f$-Divergence Inequalities via Functional Dominat…

200 papers

We prove general results about separation and weak$^\#$-convergence of boundedly finite measures on separable metric spaces and Souslin spaces. More precisely, we consider an algebra of bounded real-valued, or more generally a $*$-algebra…

Probability · Mathematics 2016-09-12 Wolfgang Löhr , Thomas Rippl

Let $G=(V(G),E(G))$ be a graph and $H=(V(H),E(H))$ be a hypergraph. The hypergraph $H$ is a {\it Berge-G} if there is a bijection $f : E(G) \mapsto E(H)$ such that for each $e \in E(G)$ we have $e \subseteq f(e)$. We define {\it dilations…

A partial differential equation governing the global evolution of the joint probability distribution of an arbitrary number of local flow observations, drawn randomly from a control volume, is derived and applied to examples involving…

Fluid Dynamics · Physics 2026-01-14 John Craske , Paul Mannix

Statistical divergence is widely applied in multimedia processing, basically due to regularity and interpretable features displayed in data. However, in a broader range of data realm, these advantages may no longer be feasible, and…

Databases · Computer Science 2020-11-20 Ruoyu Wang , Xiaobo Hu , Daniel Sun , Guoqiang Li , Raymond Wong , Shiping Chen , Jianquan Liu

We extend Fano's inequality, which controls the average probability of events in terms of the average of some $f$--divergences, to work with arbitrary events (not necessarily forming a partition) and even with arbitrary $[0,1]$--valued…

Statistics Theory · Mathematics 2019-06-12 Sebastien Gerchinovitz , Pierre Ménard , Gilles Stoltz

Bregman divergences are a class of distance-like comparison functions which play fundamental roles in optimization, statistics, and information theory. One important property of Bregman divergences is that they cause two useful formulations…

Information Theory · Computer Science 2025-01-07 Philip S. Chodrow

Metrization of statistical divergences is valuable in both theoretical and practical aspects. One approach to obtaining metrics associated with divergences is to consider their fractional powers. Motivated by this idea, Os\'an, Bussandri,…

Information Theory · Computer Science 2025-09-03 Kazuki Okamura

This paper addresses the problem of unsupervised domain adaption from theoretical and algorithmic perspectives. Existing domain adaptation theories naturally imply minimax optimization algorithms, which connect well with the domain…

Machine Learning · Computer Science 2019-07-24 Yuchen Zhang , Tianle Liu , Mingsheng Long , Michael I. Jordan

Let $G=(V, E)$ be a simple and undirected graph. For some integer $k\geq 1$, a set $D\subseteq V$ is said to be a k-dominating set in $G$ if every vertex $v$ of $G$ outside $D$ has at least $k$ neighbors in $D$. Furthermore, for some real…

Computational Complexity · Computer Science 2017-02-03 Davood Bakhshesh , Mohammad Farshi , Mahdieh Hasheminezhad

We show that the variational representations for f-divergences currently used in the literature can be tightened. This has implications to a number of methods recently proposed based on this representation. As an example application we use…

Machine Learning · Computer Science 2012-06-22 Avraham Ruderman , Mark Reid , Dario Garcia-Garcia , James Petterson

$k$-defensive domination, a variant of the classical domination problem on graphs, seeks a minimum cardinality vertex set providing a surjective defense against any attack on vertices of cardinality bounded by a parameter $k$. The problem…

Discrete Mathematics · Computer Science 2020-10-09 Tınaz Ekim , Arthur Farley , Andrzej Proskurowski , Mordechai Shalom

We study a variant of domination, called Roman domination, where we must assign to each vertex one of the labels 0, 1, or 2 and require that every vertex with label 0 has a neighbour with label 2. We study the problem of finding a low-cost…

Combinatorics · Mathematics 2024-05-07 Adrian Rettich

Causal parameters may not be point identified in the presence of unobserved confounding. However, information about non-identified parameters, in the form of bounds, may still be recovered from the observed data in some cases. We develop a…

Methodology · Statistics 2020-07-02 Noam Finkelstein , Ilya Shpitser

In this Note we introduce a new methodology for Bayesian inference through the use of $\phi$-divergences and the duality technique. The asymptotic laws of the estimates are established.

Statistics Theory · Mathematics 2011-12-30 Mohamed Cherfi

Minimum divergence problems under integral constraints appear throughout statistics and probability, including sequential inference, bandit theory, and distributionally robust optimization. In many such settings, dual representations are…

Information Theory · Computer Science 2026-03-24 Shubhanshu Shekhar , Shubhada Agrawal

This paper develops a new divergence that generalizes relative entropy and can be used to compare probability measures without a requirement of absolute continuity. We establish properties of the divergence, and in particular derive and…

Probability · Mathematics 2019-11-19 Paul Dupuis , Yixiang Mao

This paper addresses a large class of vector optimization problems in infinite-dimensional spaces with respect to two important binary relations derived from domination structures. Motivated by theoretical challenges as well as by…

Optimization and Control · Mathematics 2021-02-17 Truong Q. Bao , Boris S. Mordukhovich , Antoine Soubeyran , Christiane Tammer

This article presents a modern deterministic framework for the study of leading significant digit distributions in numerical data. Rather than relying on traditional probabilistic or mixture-based explanations, we demonstrate that the…

Machine Learning · Statistics 2025-08-20 Vladimir Berman

In this paper, we introduce the notion of (g,\Phi_{h})-convex dominated function and present some properties of them. Finally, we present a version of Hermite-Hadamard-type inequalities for (g,\Phi_{h})-convex dominated functions. Our…

Classical Analysis and ODEs · Mathematics 2012-08-07 M. Emin Ozdemir , Mustafa Gurbuz , Havva Kavurmaci

In the first part of the paper we study orthogonality, domination, weight, regular and minimal types in the contexts of rosy and super-rosy theories. Then we try to develop analogous theory for arbitrary dependent theories.

Logic · Mathematics 2011-02-19 Alf Onshuus , Alex Usvyatsov