中文
相关论文

相关论文: Mutual Information, Relative Entropy and Estimatio…

200 篇论文

While most useful information theoretic inequalities can be deduced from the basic properties of entropy or mutual information, up to now Shannon's entropy power inequality (EPI) is an exception: Existing information theoretic proofs of the…

信息论 · 计算机科学 2016-11-17 Olivier Rioul

The data processing inequality is the most basic requirement for any meaningful measure of information. It essentially states that distinguishability measures between states decrease if we apply a quantum channel and is the centerpiece of…

量子物理 · 物理学 2022-11-30 Christoph Hirche , Cambyse Rouzé , Daniel Stilck França

The classical Binary Symmetric Channel has a fixed transition probability. We discuss the Binary Symmetric Channel with a variable transition probability that depends on a Poisson distribution. The error rate for this channel is determined…

信息论 · 计算机科学 2023-07-13 A. J. Han Vinck , Fatma Rouissi

One of the basic tenets in information theory, the data processing inequality states that output divergence does not exceed the input divergence for any channel. For channels without input constraints, various estimates on the amount of…

信息论 · 计算机科学 2015-08-14 Yury Polyanskiy , Yihong Wu

The principle of maximum entropy is a broadly applicable technique for computing a distribution with the least amount of information possible while constrained to match empirically estimated feature expectations. However, in many real-world…

机器学习 · 计算机科学 2022-08-16 Kenneth Bogert , Yikang Gui , Prashant Doshi

The problem of fast point-to-point MIMO channel mutual information estimation is addressed, in the situation where the receiver undergoes unknown colored interference, whereas the channel with the transmitter is perfectly known. The…

概率论 · 数学 2012-03-14 Abla Kammoun , Romain Couillet , Jamal Najim , Merouane Debbah

From the output produced by a memoryless deletion channel from a uniformly random input of known length $n$, one obtains a posterior distribution on the channel input. The difference between the Shannon entropy of this distribution and that…

信息论 · 计算机科学 2018-08-01 Arash Atashpendar , David Mestel , A. W. Roscoe , Peter Y. A. Ryan

We examine a class of deep learning models with a tractable method to compute information-theoretic quantities. Our contributions are three-fold: (i) We show how entropies and mutual informations can be derived from heuristic statistical…

We consider the problem of signal estimation (denoising) from a statistical mechanical perspective, using a relationship between the minimum mean square error (MMSE), of estimating a signal, and the mutual information between this signal…

信息论 · 计算机科学 2016-11-17 Neri Merhav , Dongning Guo , Shlomo Shamai

The martingale part in the semimartingale decomposition of a Brownian motion with respect to an enlargement of its filtration, is an anticipative mapping of the given Brownian motion. In analogy to optimal transport theory, we define causal…

概率论 · 数学 2017-12-13 Beatrice Acciaio , Julio Backhoff Veraguas , Anastasiia Zalashko

This paper studies a class of stochastic and time-varying Gaussian intersymbol interference~(ISI) channels. The probability law for the~$i^{th}$ channel tap during time slot~$t$ is supported over an interval of centre $c_i$ and radius~$…

信息论 · 计算机科学 2022-08-16 Kamyar Moshksar

In deep learning, neural networks serve as noisy channels between input data and its representation. This perspective naturally relates deep learning with the pursuit of constructing channels with optimal performance in information…

机器学习 · 计算机科学 2022-12-06 Kangyu Weng , Aohua Cheng , Ziyang Zhang , Pei Sun , Yang Tian

Problems of probabilistic inference and decision making under uncertainty commonly involve continuous random variables. Often these are discretized to a few points, to simplify assessments and computations. An alternative approximation is…

人工智能 · 计算机科学 2013-03-08 William B. Poland , Ross D. Shachter

To provide an efficient approach to characterize the input-output mutual information (MI) under additive white Gaussian noise (AWGN) channel, this short report fits the curves of exact MI under multilevel quadrature amplitude modulation…

信息论 · 计算机科学 2019-08-27 Chongjun Ouyang , Sheng Wu , Hongwen Yang

Consider a pair of input distributions which after passing through a Poisson channel become $\epsilon$-close in total variation. We show that they must necessarily then be $\epsilon^{0.5+o(1)}$-close after passing through a Gaussian channel…

信息论 · 计算机科学 2023-06-30 Anzo Teh , Yury Polyanskiy

The mutual information (MI) between two random variables is an important correlation measure in data analysis. The Shannon entropy of a joint probability distribution is the variable part under fixed marginals. We aim to minimize and…

最优化与控制 · 数学 2025-09-08 Paula Franke , Kay Hamacher , Paul Manns

A general information transmission model, under independent and identically distributed Gaussian codebook and nearest neighbor decoding rule with processed channel output, is investigated using the performance metric of generalized mutual…

信息论 · 计算机科学 2019-08-23 Wenyi Zhang , Yizhu Wang , Cong Shen , Ning Liang

The Principle of Maximum Entropy is a rigorous technique for estimating an unknown distribution given partial information while simultaneously minimizing bias. However, an important requirement for applying the principle is that the…

信息论 · 计算机科学 2026-02-03 Kenneth Bogert , Matthew Kothe

We consider the problem of signal estimation (denoising) from a statistical-mechanical perspective, in continuation to a recent work on the analysis of mean-square error (MSE) estimation using a direct relationship between optimum…

信息论 · 计算机科学 2013-06-04 Wasim Huleihel , Neri Merhav

We propose a novel estimator of the mutual information between two ordinal vectors $x$ and $y$. Our approach is inductive (as opposed to deductive) in that it depends on the data generating distribution solely through some nonparametric…

机器学习 · 统计学 2022-04-12 Yves-Laurent Kom Samo