Note on discrimination information and variation (Corresp.)

How researchers see this paper

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

Theoretical evidence for adversarial robustness through randomization: the case of the Exponential family (2019, neutral): “Moreover, using inequality from [47], one gets:”
$f$ -Divergence Inequalities (2015, background): “Improved and generalized versions of Pinsker’s inequality have been studied, among others, in [39], [44], [46], [76], [86], [92], [104].”
Information, Divergence and Risk for Binary Experiments (2009, background): “Non-polynomial bounds are due to Vajda (1970): KL ≥ LVajda(V ) := log ( 2+V 2−V ) − 2V2+V and Toussaint (1978) who showed KL ≥ LVajda(V ) ∨ (V 2/2 + V 4/36 + V 8/288).”
Universal Estimation of Information Measures for Analog Sources (2009, unknown): “Its many properties are discussed in [183, 246, 247, 245].”