Refined Pinsker's and reverse Pinsker's inequalities for probability distributions of different dimensions

Michele Caprio

doi:10.1109/ACCESS.2022.3219851

Refined Pinsker's and reverse Pinsker's inequalities for probability distributions of different dimensions

Michele Caprio

Machine Learning and Robotics

Research output: Contribution to journal › Article › peer-review

247 Downloads (Pure)

Abstract

We provide optimal lower and upper bounds for the augmented Kullback-Leibler divergence in terms of the augmented total variation distance between two probability measures defined on two Euclidean spaces having different dimensions. We call them refined Pinsker’s and reverse Pinsker’s inequalities, respectively.

Original language	English
Journal	IEEE Access
Volume	10
DOIs	https://doi.org/10.1109/ACCESS.2022.3219851
Publication status	Published - 2022

Access to Document

10.1109/ACCESS.2022.3219851

Refined_Pinskers_and_Reverse_Pinskers_Inequalities_for_Probability_Distributions_of_Different_DimensionsFinal published version, 470 KB

Cite this

@article{b27eb6d0135d477ba0a3706687d7b9bf,

title = "Refined Pinsker's and reverse Pinsker's inequalities for probability distributions of different dimensions",

abstract = "We provide optimal lower and upper bounds for the augmented Kullback-Leibler divergence in terms of the augmented total variation distance between two probability measures defined on two Euclidean spaces having different dimensions. We call them refined Pinsker{\textquoteright}s and reverse Pinsker{\textquoteright}s inequalities, respectively.",

author = "Michele Caprio",

year = "2022",

doi = "10.1109/ACCESS.2022.3219851",

language = "English",

volume = "10",

journal = "IEEE Access",

issn = "2169-3536",

publisher = "IEEE",

}

TY - JOUR

T1 - Refined Pinsker's and reverse Pinsker's inequalities for probability distributions of different dimensions

AU - Caprio, Michele

PY - 2022

Y1 - 2022

N2 - We provide optimal lower and upper bounds for the augmented Kullback-Leibler divergence in terms of the augmented total variation distance between two probability measures defined on two Euclidean spaces having different dimensions. We call them refined Pinsker’s and reverse Pinsker’s inequalities, respectively.

AB - We provide optimal lower and upper bounds for the augmented Kullback-Leibler divergence in terms of the augmented total variation distance between two probability measures defined on two Euclidean spaces having different dimensions. We call them refined Pinsker’s and reverse Pinsker’s inequalities, respectively.

U2 - 10.1109/ACCESS.2022.3219851

DO - 10.1109/ACCESS.2022.3219851

M3 - Article

SN - 2169-3536

VL - 10

JO - IEEE Access

JF - IEEE Access

ER -

Refined Pinsker's and reverse Pinsker's inequalities for probability distributions of different dimensions

Abstract

Access to Document

Fingerprint

Cite this