On Study of Mutual Information and its Estimation Methods

06/21/2021
by   Marshal Arijona Sinaga, et al.
0

The presence of mutual information in the research of deep learning has grown significantly. It has been proven that mutual information can be a good objective function to build a robust deep learning model. Most of the researches utilize estimation methods to approximate the true mutual information. This technical report delivers an extensive study about definitions as well as properties of mutual information. This article then delivers some reviews and current drawbacks of mutual information estimation methods afterward.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
06/13/2019

Factorized Mutual Information Maximization

We investigate the sets of joint probability distributions that maximize...
research
05/18/2021

A note on the unbiased estimation of mutual information

Estimators for mutual information are typically biased. However, in the ...
research
04/22/2019

Learning gradient-based ICA by neurally estimating mutual information

Several methods of estimating the mutual information of random variables...
research
08/30/2023

Towards a Rigorous Analysis of Mutual Information in Contrastive Learning

Contrastive learning has emerged as a cornerstone in recent achievements...
research
01/28/2018

Probability Mass Exclusions and the Directed Components of Pointwise Mutual Information

The pointwise mutual information quantifies the mutual information betwe...
research
03/15/2022

On Suspicious Coincidences and Pointwise Mutual Information

Barlow (1985) hypothesized that the co-occurrence of two events A and B ...
research
01/20/2019

NIF: A Framework for Quantifying Neural Information Flow in Deep Networks

In this paper, we present a new approach to interpreting deep learning m...

Please sign up or login with your details

Forgot password? Click here to reset