English
Related papers

Related papers: $H(X)$ vs. $H(f(X))$

200 papers

We study best-policy identification for finite-horizon risk-sensitive reinforcement learning under the entropic risk measure. Recent work established a constant gap in the exponential horizon dependence between lower and upper bounds on the…

Machine Learning · Computer Science 2026-05-14 Amer Essakine , Claire Vernade

We introduce an axiomatic approach to entropies and relative entropies that relies only on minimal information-theoretic axioms, namely monotonicity under mixing and data-processing as well as additivity for product distributions. We find…

Information Theory · Computer Science 2021-09-22 Gilad Gour , Marco Tomamichel

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

Dependence among marginally constrained observations can break a finite-sample barrier. To formalize this phenomenon, we introduce the \emph{minimum list entropy coupling} $H(P\|Q_1,\dots,Q_m)$, the minimum conditional entropy…

Information Theory · Computer Science 2026-05-18 Shahab Asoodeh , Jun Chen

Generalized entropies and relative entropies are the subject of active research. Similar to the standard relative entropy, the relative $q$-entropy is generally unbounded for $q>1$. Upper bounds on the quantum relative $q$-entropy in terms…

Mathematical Physics · Physics 2011-06-28 Alexey E. Rastegin

We consider distributions of ordered random vectors with given one-dimensional marginal distributions. We give an elementary necessary and sufficient condition for the existence of such a distribution with finite entropy. In this case, we…

Statistics Theory · Mathematics 2015-09-08 Cristina Butucea , Jean-François Delmas , Anne Dutfoy , Richard Fischer

Upper and lower bounds are obtained for the joint entropy of a collection of random variables in terms of an arbitrary collection of subset joint entropies. These inequalities generalize Shannon's chain rule for entropy as well as…

Information Theory · Computer Science 2024-05-07 Mokshay Madiman , Prasad Tetali

Let $0 < \epsilon < 1/2$ be a noise parameter, and let $T_{\epsilon}$ be the noise operator acting on functions on the boolean cube $\{0,1\}^n$. Let $f$ be a nonnegative function on $\{0,1\}^n$. We upper bound the entropy of $T_{\epsilon}…

Information Theory · Computer Science 2016-06-23 Alex Samorodnitsky

The "extremal function" $c(H)$ of a graph $H$ is the supremum of densities of graphs not containing $H$ as a minor, where the "density" of a graph $G$ is the ratio of the number of edges to the number of vertices. Myers and Thomason (2005),…

Combinatorics · Mathematics 2022-07-25 Kevin Hendrey , Sergey Norin , David R. Wood

Hal\'asz's Theorem gives an upper bound for the mean value of a multiplicative function $f$. The bound is sharp for general such $f$, and, in particular, it implies that a multiplicative function with $|f(n)|\le 1$ has either mean value…

Number Theory · Mathematics 2019-02-20 Andrew Granville , Adam J Harper , K. Soundararajan

Concentration inequalities are fundamental tools in probabilistic combinatorics and theoretical computer science for proving that random functions are near their means. Of particular importance is the case where f(X) is a function of…

Combinatorics · Mathematics 2022-06-01 Lutz Warnke

We develop an approximation method for the differential entropy $h(\mathbf{X})$ of a $q$-component Gaussian mixture in $\mathbb{R}^n$. We provide two examples of approximations using our method denoted by…

Information Theory · Computer Science 2025-05-07 Basheer Joudeh , Boris Škorić

We prove a variety of new and refined uniform continuity bounds for entropies of both classical random variables on an infinite state space and of quantum states of infinite-dimensional systems. We obtain the first tight continuity estimate…

Quantum Physics · Physics 2024-11-20 Simon Becker , Nilanjana Datta , Michael G. Jabbour

Entropy rate is a real valued functional on the space of discrete random sources which lacks a closed formula even for subclasses of sources which have intuitive parameterizations. A good way to overcome this problem is to examine its…

Information Theory · Computer Science 2015-01-14 Alexander Schönhuth

The existing upper and lower bounds between entropy and error are mostly derived through an inequality means without linking to joint distributions. In fact, from either theoretical or application viewpoint, there exists a need to achieve a…

Information Theory · Computer Science 2013-03-06 Bao-Gang Hu , Hong-Jie Xing

We provide a sharp lower bound on the $p$-norm of a sum of independent uniform random variables in terms of its variance when $0 < p < 1$. We address an analogous question for $p$-R\'enyi entropy for $p$ in the same range.

Probability · Mathematics 2025-01-28 Giorgos Chasapis , Keerthana Gurushankar , Tomasz Tkocz

In this paper relations among some kinds of cumulative entropies and moments of order statistics are presented. By using some characterizations and the symmetry of a non negative and absolutely continuous random variable X, lower and upper…

Statistics Theory · Mathematics 2020-09-07 Narayanaswamy Balakrishnan , Francesco Buono , Maria Longobardi

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…

Information Theory · Computer Science 2026-02-03 Kenneth Bogert , Matthew Kothe

The existing upper and lower bounds between entropy and error probability are mostly derived from the inequality of the entropy relations, which could introduce approximations into the analysis. We derive analytical bounds based on the…

Information Theory · Computer Science 2012-05-31 Bao-Gang Hu , Hong-Jie Xing

Computational pseudorandomness studies the extent to which a random variable $\bf{Z}$ looks like the uniform distribution according to a class of tests $\cal{F}$. Computational entropy generalizes computational pseudorandomness by studying…

Computational Complexity · Computer Science 2020-11-13 Russell Impagliazzo , Sam McGuire
‹ Prev 1 3 4 5 6 7 10 Next ›