English
Related papers

Related papers: Minimum--Entropy Couplings and their Applications

200 papers

In this work, we study non-parametric estimation of joint probabilities of a given set of discrete and continuous random variables from their (empirically estimated) 2D marginals, under the assumption that the joint probability could be…

Machine Learning · Computer Science 2022-03-04 Shaan ul Haque , Ajit Rajwade , Karthik S. Gurumoorthy

We develop the method of Maximum Entropy (ME) as a technique to generate approximations to probability distributions. The central results consist in (a) justifying the use of relative entropy as the uniquely natural criterion to select a…

Statistical Mechanics · Physics 2007-07-24 Chih-Yuan Tseng , Ariel Caticha

The principle of maximum entropy is a broadly applicable technique for computing a distribution with the least amount of information possible constrained to match empirical data, for instance, feature expectations. We seek to generalize…

Information Theory · Computer Science 2022-05-30 Kenneth Bogert

The principle of maximum entropy provides a useful method for inferring statistical mechanics models from observations in correlated systems, and is widely used in a variety of fields where accurate data are available. While the assumptions…

Neurons and Cognition · Quantitative Biology 2017-06-02 Ulisse Ferrari , Tomoyuki Obuchi , Thierry Mora

We show how to determine the maximum and minimum possible values of one measure of entropy for a given value of another measure of entropy. These maximum and minimum values are obtained for two standard forms of probability distribution (or…

Quantum Physics · Physics 2007-05-23 Dominic W. Berry , Barry C. Sanders

Given a point $A$ in the convex hull of a given adjoint orbit $\mathcal{O}(F)$ of a compact Lie group $G$, we give a polynomial time algorithm to compute the probability density supported on $\mathcal{O}(F)$ whose expectation is $A$ and…

Optimization and Control · Mathematics 2020-11-04 Jonathan Leake , Nisheeth K. Vishnoi

Two new information-theoretic methods are introduced for establishing Poisson approximation inequalities. First, using only elementary information-theoretic techniques it is shown that, when $S_n=\sum_{i=1}^nX_i$ is the sum of the (possibly…

Probability · Mathematics 2010-10-21 Ioannis Kontoyiannis , Peter Harremoes , Oliver Johnson

Let $G_1,\dots, G_m$ be independent Bernoulli random subgraphs of the complete graph ${\cal K}_n$ having variable sizes $x_1,\dots, x_m\in [n]$ and densities $q_1,\dots, q_m\in [0,1]$. Letting $n,m\to+\infty$, we study the connectivity…

Probability · Mathematics 2023-11-08 Daumilas Ardickas , Mindaugas Bloznelis

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

In this paper, the joint distribution of the sum and maximum of independent, not necessarily identically distributed, nonnegative random variables is studied for two cases: i) continuous and ii) discrete random variables. First, a recursive…

Probability · Mathematics 2024-07-01 Christos N. Efrem

The Expectation-Maximization (EM) algorithm for mixture models often results in slow or invalid convergence. The popular convergence proof affirms that the likelihood increases with Q; Q is increasing in the M -step and non-decreasing in…

Machine Learning · Computer Science 2018-10-29 Chenguang Lu

We consider estimating the Shannon entropy of a discrete distribution $P$ from $n$ i.i.d. samples. Recently, Jiao, Venkat, Han, and Weissman, and Wu and Yang constructed approximation theoretic estimators that achieve the minimax $L_2$…

Information Theory · Computer Science 2019-01-03 Yanjun Han , Jiantao Jiao , Tsachy Weissman

It is well established that the notion of min-entropy fails to satisfy the \emph{chain rule} of the form $H(X,Y) = H(X|Y)+H(Y)$, known for Shannon Entropy. Such a property would help to analyze how min-entropy is split among smaller blocks.…

Information Theory · Computer Science 2017-03-01 Maciej Skorski

Joint probability mass function (PMF) estimation is a fundamental machine learning problem. The number of free parameters scales exponentially with respect to the number of random variables. Hence, most work on nonparametric PMF estimation…

Machine Learning · Computer Science 2021-03-25 Jian Vora , Karthik S. Gurumoorthy , Ajit Rajwade

We define and investigate a notion of entropy for quantum error correcting codes. The entropy of a code for a given quantum channel has a number of equivalent realisations, such as through the coefficients associated with the Knill-Laflamme…

Quantum Physics · Physics 2009-02-24 David W. Kribs , Aron Pasieka , Karol Zyczkowski

Random geometric graphs (RGGs) are commonly used to model networked systems that depend on the underlying spatial embedding. We concern ourselves with the probability distribution of an RGG, which is crucial for studying its random…

Information Theory · Computer Science 2018-01-16 Mihai-Alin Badiu , Justin P. Coon

Nonuniform subsampling methods are effective to reduce computational burden and maintain estimation efficiency for massive data. Existing methods mostly focus on subsampling with replacement due to its high computational efficiency. If the…

Methodology · Statistics 2021-07-06 Jun Yu , HaiYing Wang , Mingyao Ai , Huiming Zhang

An axiomatic foundation regarding the entropy for complex systems is established. Missing from decades of research was the requirement that entropy must measure the uncertainty at the informational scale of the maximizing distribution,…

Statistical Mechanics · Physics 2026-05-29 Kenric P. Nelson

Many quantum information measures can be written as an optimization of the quantum relative entropy between sets of states. For example, the relative entropy of entanglement of a state is the minimum relative entropy to the set of separable…

Quantum Physics · Physics 2018-08-09 Hamza Fawzi , Omar Fawzi

A well-known result across information theory, machine learning, and statistical physics shows that the maximum entropy distribution under a mean constraint has an exponential form called the Gibbs-Boltzmann distribution. This is used for…

Machine Learning · Computer Science 2020-06-26 Amir R. Asadi , Emmanuel Abbe