Generalized Csiszár's f-divergence for Lipschitzian functions
نویسندگان
چکیده
منابع مشابه
Fixed Point Theorems for Generalized Lipschitzian Semigroups
Let K be a nonempty subset of a p-uniformly convex Banach space E, G a left reversible semitopological semigroup, and = {Tt : t ∈G} a generalized Lipschitzian semigroup of K into itself, that is, for s ∈ G, ‖Tsx−Tsy‖ ≤ as‖x−y‖+bs(‖x−Tsx‖+ ‖y−Tsy‖)+cs(‖x−Tsy‖+‖y−Tsx‖), for x,y ∈ K where as,bs ,cs > 0 such that there exists a t1 ∈ G such that bs +cs < 1 for all s t1. It is proved that if there ex...
متن کاملMixed f - divergence and inequalities for log concave functions ∗
Mixed f -divergences, a concept from information theory and statistics, measure the difference between multiple pairs of distributions. We introduce them for log concave functions and establish some of their properties. Among them are affine invariant vector entropy inequalities, like new Alexandrov-Fenchel type inequalities and an affine isoperimetric inequality for the vector form of the Kull...
متن کاملOn Uniformly Generalized Lipschitzian Mappings
We consider another class of generalized Lipschitzian type mappings and utilize the same to prove fixed point theorems for asymptotically regular and uniformly generalized Lipschitzian one-parameter semigroups of self-mappings defined on bounded metric spaces equipped with uniform normal structure which yield corresponding results in respect of semigroup of iterates of a self-mapping as corolla...
متن کاملClarke Subgradients for Directionally Lipschitzian Stratifiable Functions
Using a geometric argument, we show that under a reasonable continuity condition, the Clarke subdifferential of a semi-algebraic (or more generally stratifiable) directionally Lipschitzian function admits a simple form: the normal cone to the domain and limits of gradients generate the entire Clarke subdifferential. The characterization formula we obtain unifies various apparently disparate res...
متن کاملF-divergence Is a Generalized Invariant Measure between Distributions
Finding measures (or features) invariant to inevitable variations caused by non-linguistical factors (transformations) is a fundamental yet important problem in speech recognition. Recently, Minematsu [1, 2] proved that Bhattacharyya distance (BD) between two distributions is invariant to invertible transforms on feature space, and develop an invariant structural representation of speech based ...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Mathematical Inequalities & Applications
سال: 2021
ISSN: 1331-4343
DOI: 10.7153/mia-2021-24-02