On Measures of Information and Their Characterizations

By J. Aczél, J. Daróczy. 2012

336 citations recorded by the source corpus.

How researchers see this paper

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

Maximum Lq-likelihood estimation. (2010, methodology): “When q is properly chosen for small and moderate sample sizes, the MLqE can successfully trade bias for precision, resulting in a substantial reduction of the mean squared error.”
RUSBoost: A Hybrid Approach to Alleviating Class Imbalance (2010, methodology): “C4.5 [27] is a decision tree learner that uses an entropy-based splitting criterion stemming from information theory [ 28 ].”
Of Bits and Wows: A Bayesian Theory of Surprise with Applications to Attention (2009, methodology): “While several approaches for quantifying information have been proposed, the most prominent one so far has been Claude Shannon's definition introduced over half a century ago (Aczel & Daroczy, 1975; Blahut, 1987; Cover & Thomas, 1991; McEliece, 1977; Shannon, 1948).”
Rényi Divergence and Kullback-Leibler Divergence (2012, result): “ith the Copenhagen Business College, Denmark. Some of the results in this paper have previously been presented at the ISIT 2010 conference. Although the closely related R´enyi entropy is well studied [14], [15], the properties of Renyi divergence are scattered´ throughout the literature and have oft”