Information Measures: Information and its Description in Science and Engineering

By C. Arndt. 2001

165 citations recorded by the source corpus.

Subfields: Computational Theory and Mathematics, Statistical and Nonlinear Physics

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computational Theory and Mathematics

In Statistical and Nonlinear Physics

Citations in the corpus

Multiple-Source Adaptation with Domain Classifiers (2020, background): “It can be shown that the Rényi Divergence is always non-negative and that for any α > 0, Dα(D ‖ D′) = 0 iff D = D′ [Arndt, 2004].”
Algorithms and Theory for Multiple-Source Adaptation (2018, background): “It can be shown that the Rényi Divergence is always non-negative and that for any α > 0, Dα(D ∥D′) = 0 iff D =D′ (Arndt, 2004).”
Multiple Source Adaptation and the Rényi Divergence (2009, background): “Much of our results are based on a family of information theoretical divergences introduced by Alfred R´enyi [1], which share some of the properties of the standard relative entropy or Kullback-Leibler divergence and include it as a special case, but form an extension based on the theory of…”
A survey of multi-source domain adaptation (2015, background): “Such learning task is known as domain adaptation [3, 4, 5, 6, 7, 8], which is confronted in many applications, like computer vision [9, 10, 11, 12], sentimental analysis [13, 14, 15, 16], natural language processing [17], video concept detection [18, 19], and wiﬁ localization detection [20].”
Multiple-source adaptation theory and algorithms (2020, background): “It can be shown that the Rényi Divergence is always non-negative and that for any α > 0, Dα(D ∥ D′) = 0 iff D = D′ [Arndt, 2004].”
Power laws in elementary and heavy-ion collisions (2008, background): “investigate the possibility of replacing the usual statistical model based on BG entropy, SBG, by its modified version based on some other form of entropy discussed in the literature [7].”
Rényi divergence measures for commonly used univariate continuous distributions (2013, background): “While a significant number of other divergence measures have since been introduced [1, 3, 9], Rényi divergences are especially important because of their generality, applicability, and the fact that they posses operational definitions in the context of hypothesis testing [7, 2] as well as coding [14”
Wisdom of crowds for robust gene network inference (2012, methodology): “(5) The final chip ordering was given by the ordering thus obtained, subject to a manual correction to enforce the natural ordering of time series and perturbation dilution series as a rigid constraint.”
Learning Bounds for Importance Weighting (2010, unknown): “The following theorem provides a more favorable bound as a function of the ratio M/m when any of the moments of w, dα+1(P‖Q), is finite, which is the case when d∞(P‖Q) < ∞ since the Rényi divergence is a non-decreasing function of α [23, 2], in particular: ∀α > 0, dα+1(P‖Q) ≤ d∞(P‖Q).”