中文
相关论文

相关论文: On the Estimation of Information Measures of Conti…

200 篇论文

We extend previously proposed measures of complexity, emergence, and self-organization to continuous distributions using differential entropy. This allows us to calculate the complexity of phenomena for which distributions are known. We…

适应与自组织系统 · 物理学 2016-04-01 Guillermo Santamaría-Bonfil , Nelson Fernández , Carlos Gershenson

Most entropy measures depend on the spread of the probability distribution over the sample space $\mathcal{X}$, and the maximum entropy achievable scales proportionately with the sample space cardinality $|\mathcal{X}|$. For a finite…

机器学习 · 计算机科学 2023-05-25 Rohan Ghosh , Mehul Motani

Entropy is a measure of heterogeneity widely used in applied sciences, often when data are collected over space. Recently, a number of approaches has been proposed to include spatial information in entropy. The aim of entropy is to…

统计理论 · 数学 2019-11-12 Linda Altieri , Daniela Cocchi , Giulia Roli

A novel, non-trivial, probabilistic upper bound on the entropy of an unknown one-dimensional distribution, given the support of the distribution and a sample from that distribution, is presented. No knowledge beyond the support of the…

信息论 · 计算机科学 2007-07-13 Joseph DeStefano , Erik Learned-Miller

We seek an entropy estimator for discrete distributions with fully empirical accuracy bounds. As stated, this goal is infeasible without some prior assumptions on the distribution. We discover that a certain information moment assumption…

信息论 · 计算机科学 2022-12-27 Doron Cohen , Aryeh Kontorovich , Aaron Koolyk , Geoffrey Wolfer

We study the fundamental task of estimating the median of an underlying distribution from a finite number of samples, under pure differential privacy constraints. We focus on distributions satisfying the minimal assumption that they have a…

Entropy and differential entropy are important quantities in information theory. A tractable extension to singular random variables-which are neither discrete nor continuous-has not been available so far. Here, we present such an extension…

信息论 · 计算机科学 2017-01-04 Günther Koliander , Georg Pichler , Erwin Riegler , Franz Hlawatsch

We study the problem of overcoming exponential sample complexity in differential entropy estimation under Gaussian convolutions. Specifically, we consider the estimation of the differential entropy $h(X+Z)$ via $n$ independently and…

信息论 · 计算机科学 2023-05-12 Kristjan Greenewald , Brian Kingsbury , Yuancheng Yu

We study the problem of estimating a distribution over a finite alphabet from an i.i.d. sample, with accuracy measured in relative entropy (Kullback-Leibler divergence). While optimal bounds on the expected risk are known, high-probability…

统计理论 · 数学 2026-02-27 Jaouad Mourtada

Mixture distributions are a workhorse model for multimodal data in information theory, signal processing, and machine learning. Yet even when each component density is simple, the differential entropy of the mixture is notoriously hard to…

信息论 · 计算机科学 2026-02-18 Namyoon Lee

Determining the strength of non-linear statistical dependencies between two variables is a crucial matter in many research fields. The established measure for quantifying such relations is the mutual information. However, estimating mutual…

数据分析、统计与概率 · 物理学 2019-07-24 Damián G. Hernández , Inés Samengo

Estimating the Shannon entropy of a discrete distribution from which we have only observed a small sample is challenging. Estimating other information-theoretic metrics, such as the Kullback-Leibler divergence between two sparsely sampled…

数据分析、统计与概率 · 物理学 2023-02-24 Angelo Piga , Lluc Font-Pomarol , Marta Sales-Pardo , Roger Guimerà

A method for estimating the Shannon differential entropy of multidimensional random variables using independent samples is described. The method is based on decomposing the distribution into a product of the marginal distributions and the…

统计力学 · 物理学 2020-04-22 Gil Ariel , Yoram Louzoun

Entropy estimation is of practical importance in information theory and statistical science. Many existing entropy estimators suffer from fast growing estimation bias with respect to dimensionality, rendering them unsuitable for…

信息论 · 计算机科学 2023-08-22 Ziqiao Ao , Jinglai Li

The maximum entropy principle is a powerful tool for solving underdetermined inverse problems. This paper considers the problem of discretizing a continuous distribution, which arises in various applied fields. We obtain the approximating…

数值分析 · 数学 2020-08-05 Ken'ichiro Tanaka , Alexis Akira Toda

Entropy-type integral functionals of densities are widely used in mathematical statistics, information theory, and computer science. Examples include measures of closeness between distributions (e.g., density power divergence) and…

统计理论 · 数学 2013-03-08 David Källberg , Oleg Seleznjev

Bayesian optimal experimental design provides a principled framework for selecting experimental settings that maximize obtained information. In this work, we focus on estimating the expected information gain in the setting where the…

机器学习 · 统计学 2025-10-02 Chuntao Chen , Tapio Helin , Nuutti Hyvönen , Yuya Suzuki

We consider an extension of $\epsilon$-entropy to a KL-divergence based complexity measure for randomized density estimation methods. Based on this extension, we develop a general information-theoretical inequality that measures the…

统计理论 · 数学 2007-06-13 Tong Zhang

Estimating mutual information from observed samples is a basic primitive, useful in several machine learning tasks including correlation mining, information bottleneck clustering, learning a Chow-Liu tree, and conditional independence…

信息论 · 计算机科学 2018-10-11 Weihao Gao , Sreeram Kannan , Sewoong Oh , Pramod Viswanath

The profile of a sample is the multiset of its symbol frequencies. We show that for samples of discrete distributions, profile entropy is a fundamental measure unifying the concepts of estimation, inference, and compression. Specifically,…

机器学习 · 统计学 2020-02-27 Yi Hao , Alon Orlitsky
‹ 上一页 1 2 3 10 下一页 ›