Update of a conditional probability by minimal divergence

11/01/2019
by   Jan Naudts, et al.
0

The present paper investigates the situation that two events which are believed to be independent become statistically dependent during a subsequent observation or measurement. The situation is well-known in quantum statistics but occurs in many other contexts as well. The optimal update is obtained by minimizing either the Hellinger distance or the quadratic Bregman divergence. The results obtained by the two methods differ.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
01/14/2022

Test-measured Rényi divergences

One possibility of defining a quantum Rényi α-divergence of two quantum ...
research
08/24/2022

Maintaining Optimality in Assignment Problem against Weight Updates around Vertices

We consider a dynamic situation in the weighted bipartite matching probl...
research
10/03/2018

Sum decomposition of divergence into three divergences

Divergence functions play a key role as to measure the discrepancy betwe...
research
11/11/2021

Reliability Function of Quantum Information Decoupling

Quantum information decoupling is an important quantum information proce...
research
02/02/2013

Sharp Inequalities for f-divergences

f-divergences are a general class of divergences between probability mea...
research
02/13/2018

First Order Generative Adversarial Networks

GANs excel at learning high dimensional distributions, but they can upda...
research
06/29/2019

Statistical estimation of the Kullback-Leibler divergence

Wide conditions are provided to guarantee asymptotic unbiasedness and L^...

Please sign up or login with your details

Forgot password? Click here to reset