The Entropy Method in Large Deviation Theory

10/24/2022
by   Lei Yu, et al.
0

This paper illustrates the power of the entropy method in addressing problems from large deviation theory. We provide and review entropy proofs for most fundamental results in large deviation theory, including Cramer's theorem, the Gärtner–Ellis theorem, and Sanov's theorem. Moreover, by the entropy method, we also strengthen Sanov's theorem to the strong version.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
10/10/2022

A Reunion of Godel, Tarski, Carnap, and Rosser

We unify Godel's First Incompleteness Theorem (1931), Tarski's Undefinab...
research
10/13/2019

A Large-Deviation Upperbound on Directed Last-Passage Percolation Growth Rate Based on Entropy of Direction Vector

This short note provides a large-deviation-based upper bound on the grow...
research
07/27/2023

On the impossibility of discovering a formula for primes using AI

The present work explores the theoretical limits of Machine Learning (ML...
research
04/24/2019

Maximum Entropy Based Significance of Itemsets

We consider the problem of defining the significance of an itemset. We s...
research
06/26/2003

Classical and Nonextensive Information Theory

In this work we firstly review some results in Classical Information The...
research
03/26/2020

Moderate deviation theorem for the Neyman-Pearson statistic in testing uniformity

We show that for local alternatives to uniformity which are determined b...
research
12/22/2020

A generalization of Costa's Entropy Power Inequality

Aim of this short note is to study Shannon's entropy power along entropi...

Please sign up or login with your details

Forgot password? Click here to reset