A Note on Integral Probability Metrics and φ-divergences
نویسندگان
چکیده
We study some connections between integral probability metrics [21] of the form, γF(P,Q) := sup f∈F ̨
منابع مشابه
On Integral Probability Metrics, φ-Divergences and Binary Classification
φ-divergences are a widely studied class of distance measures between probabilities. In this paper, a different class of distance measures on probabilities, called the integral probability metrics (IPMs) is considered. IPMs, for example, the Wasserstein distance and Dudley metric have, thus far, only been used in a limited setting, as theoretical tools in mass transportation problems, in metriz...
متن کاملOn integral probability metrics, \phi-divergences and binary classification
A class of distance measures on probabilities — the integral probability metrics (IPMs) — is addressed: these include the Wasserstein distance, Dudley metric, and Maximum Mean Discrepancy. IPMs have thus far mostly been used in more abstract settings, for instance as theoretical tools in mass transportation problems, and in metrizing the weak topology on the set of all Borel probability measure...
متن کاملCOUPLED FIXED POINT THEOREMS FOR GENERALIZED Φ-MAPPINGS SATISFYING CONTRACTIVE CONDITION OF INTEGRAL TYPE ON CONE METRIC SPACES
In this paper, we unify, extend and generalize some results on coupled fixed point theorems of generalized φ- mappings with some applications to fixed points of integral type mappings in cone metric spaces.
متن کاملΦ - Divergences , Sufficiency , Bayes Sufficiency , and Deficiency
The paper studies the relations between φ-divergences and fundamental concepts of decision theory such as sufficiency, Bayes sufficiency, and LeCam’s deficiency. A new and considerably simplified approach is given to the spectral representation of φ-divergences already established in Österreicher and Feldman [28] under restrictive conditions and in Liese and Vajda [22], [23] in the general form...
متن کاملSymmetrized Bregman Divergences and Metrics
While Bregman divergences [3] have been used for several machine learning problems in recent years, the facts that they are asymmetric and does not satisfy triangle inequality have been a major limitation. In this paper, we investigate the relationship between two families of symmetrized Bregman divergences and metrics, which satisfy the triangle inequality. Further, we investigate kmeans-type ...
متن کامل