Fisher Information and Logarithmic Sobolev Inequality for Matrix Valued Functions

07/23/2018
by   Li Gao, et al.
0

We prove a version of Talagrand's concentration inequality for subordinated sub-Laplacian on a compact Riemannian manifold using tools from noncommutative geometry. As an application, motivated by quantum information theory, we show that on a finite dimensional matrix algebra the set of self-adjoint generators satisfying a tensor stable modified logarithmic Sobolev inequality is dense.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
08/12/2020

A matrix concentration inequality for products

We present a non-asymptotic concentration inequality for the random matr...
research
01/05/2022

Secrecy Outage Probability: Revisited

This paper technically explores the secrecy outage probability (SOP) Λ a...
research
09/19/2023

On the categorical foundations of quantum information theory: Categories and the Cramer-Rao inequality

An extension of Cencov's categorical description of classical inference ...
research
06/21/2023

A formalization of the CHSH inequality and Tsirelson's upper-bound in Isabelle/HOL

We present a formalization of several fundamental notions and results fr...
research
10/21/2020

Riemannian Langevin Algorithm for Solving Semidefinite Programs

We propose a Langevin diffusion-based algorithm for non-convex optimizat...
research
12/20/2019

A vector-contraction inequality for Rademacher complexities using p-stable variables

Andreas Maurer in the paper "A vector-contraction inequality for Rademac...
research
05/29/2018

Unification and Logarithmic Space

We present an algebraic characterization of the complexity classes Logsp...

Please sign up or login with your details

Forgot password? Click here to reset