English
Related papers

Related papers: Nested Inequalities Among Divergence Measures

200 papers

We present a unified technique for sequential estimation of convex divergences between distributions, including integral probability metrics like the kernel maximum mean discrepancy, $\varphi$-divergences like the Kullback-Leibler…

Statistics Theory · Mathematics 2023-03-14 Tudor Manole , Aaditya Ramdas

Tight bounds for several symmetric divergence measures are introduced, given in terms of the total variation distance. Each of these bounds is attained by a pair of 2 or 3-element probability distributions. An application of these bounds…

Information Theory · Computer Science 2016-11-15 Igal Sason

While the slogan "no measurement without disturbance" has established itself under the name Heisenberg effect in the consciousness of the scientifically interested public, a precise statement of this fundamental feature of the quantum world…

Quantum Physics · Physics 2013-10-24 Paul Busch , Pekka Lahti , Reinhard F. Werner

We characterize Martin-L\"of randomness and Schnorr randomness in terms of the merging of opinions, along the lines of the Blackwell-Dubins Theorem. After setting up a general framework for defining notions of merging randomness, we focus…

Logic · Mathematics 2026-03-10 Simon M. Huttegger , Sean Walsh , Francesca Zaffora Blando

We formulate a new information-theoretic principle--the shifted composition rule--which bounds the divergence (e.g., Kullback-Leibler or R\'enyi) between the laws of two stochastic processes via the introduction of auxiliary shifts. In this…

Probability · Mathematics 2023-11-27 Jason M. Altschuler , Sinho Chewi

We investigate how basic probability inequalities can be extended to an imprecise framework, where (precise) probabilities and expectations are replaced by imprecise probabilities and lower/upper previsions. We focus on inequalities giving…

Probability · Mathematics 2022-11-04 Renato Pelessoni , Paolo Vicig

We propose a new skewness test statistic for normality based on the Pearson measure of skewness. We obtain asymptotic first four moments of the null distribution for this statistic by using a computer algebra system and its normalizing…

Computation · Statistics 2012-02-24 Shigekazu Nakagawa , Hiroki Hashiguchi , Naoto Niki

In 1998, Zhang and Yeung found the first unconditional non-Shannon-type information inequality. Recently, Dougherty, Freiling and Zeger gave six new unconditional non-Shannon-type information inequalities. This work generalizes their work…

Information Theory · Computer Science 2008-05-01 Weidong Xu , Jia Wang , Jun Sun

Here I present the analytic form of two common distance metrics, the symmetrised Kullback-Leibler Divergence and the Kolmogorov-Smirnov statistic, as well as an extension of the Kolmogorov-Smirnov statistic for comparing theoretical gamma…

Statistics Theory · Mathematics 2018-02-06 Colin M. McCrimmon

Statistical distances (SDs), which quantify the dissimilarity between probability distributions, are central to machine learning and statistics. A modern method for estimating such distances from data relies on parametrizing a variational…

Statistics Theory · Mathematics 2021-03-18 Sreejith Sreekumar , Zhengxin Zhang , Ziv Goldfeld

We introduce a novel parametric family of symmetric information-theoretic distances based on Jensen's inequality for a convex functional generator. In particular, this family unifies the celebrated Jeffreys divergence with the…

Computer Vision and Pattern Recognition · Computer Science 2011-12-20 Frank Nielsen

Quantifying the difference between probability distributions is crucial in machine learning. However, estimating statistical divergences from empirical samples is challenging due to unknown underlying distributions. This work proposes the…

Machine Learning · Computer Science 2024-10-25 Jhoan K. Hoyos-Osorio , Luis G. Sanchez-Giraldo

Recently, Chen and Sbert proposed a general divergence measure. This report presents some interim findings about the question whether the divergence measure is a metric or not. It has been postulated that (i) the measure might be a metric…

Information Theory · Computer Science 2021-01-18 Min Chen , Mateu Sbert

The geometric Jensen--Shannon divergence (G-JSD) gained popularity in machine learning and information sciences thanks to its closed-form expression between Gaussian distributions. In this work, we introduce an alternative definition of the…

Information Theory · Computer Science 2025-09-19 Frank Nielsen

Any physical system can be viewed from the perspective that information is implicitly represented in its state. However, the quantification of this information when it comes to complex networks has remained largely elusive. In this work, we…

Physics and Society · Physics 2016-12-23 Manlio De Domenico , Jacob Biamonte

We investigate and compare three distinguished geometric measures of bipartite quantum correlations that have been recently introduced in the literature: the geometric discord, the measurement-induced geometric discord, and the discord of…

Quantum Physics · Physics 2016-05-26 Wojciech Roga , Dominique Spehner , Fabrizio Illuminati

The Jensen's inequality plays a crucial role in the analysis of time-delay and sampled-data systems. Its conservatism is studied through the use of the Gr\"{u}ss Inequality. It has been reported in the literature that fragmentation (or…

Systems and Control · Computer Science 2012-04-06 Corentin Briat

In a variety of applications it is important to extract information from a probability measure $\mu$ on an infinite dimensional space. Examples include the Bayesian approach to inverse problems and possibly conditioned) continuous time…

Probability · Mathematics 2016-06-02 Frank Pinski , Gideon Simpson , Andrew Stuart , Hendrik Weber

In the study of Heisenberg's error-disturbance relation, it is commonly believed that the non-unitary change of states hinders us from deducing the information encoded in original states about subsequently measured observable. However, we…

Quantum Physics · Physics 2014-10-30 Liang-Liang Sun , Yong-Shun Song , Zhi-Xin Chen , Cong-Feng Qiao

Algorithmic bias is of increasing concern, both to the research community, and society at large. Bias in AI is more abstract and unintuitive than traditional forms of discrimination and can be more difficult to detect and mitigate. A clear…

Machine Learning · Computer Science 2021-10-12 Cody Blakeney , Gentry Atkinson , Nathaniel Huish , Yan Yan , Vangelis Metris , Ziliang Zong
‹ Prev 1 3 4 5 6 7 10 Next ›