Strong Asymptotic Composition Theorems for Sibson Mutual Information

05/12/2020
by   Benjamin Wu, et al.
0

We characterize the growth of the Sibson mutual information, of any order that is at least unity, between a random variable and an increasing set of noisy, conditionally independent observations of the random variable. The Sibson mutual information increases to an order-dependent limit exponentially fast, with an exponent that is order-independent. The result is contrasted with composition theorems in differential privacy.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
02/22/2022

Error Exponent and Strong Converse for Quantum Soft Covering

How well can we approximate a quantum channel output state using a rando...
research
11/25/2020

Bounds for Algorithmic Mutual Information and a Unifilar Order Estimator

Inspired by Hilberg's hypothesis, which states that mutual information b...
research
11/26/2018

Divergence radii and the strong converse exponent of classical-quantum channel coding with constant compositions

There are different inequivalent ways to define the Rényi mutual informa...
research
08/22/2023

Equivalence Principle of the P-value and Mutual Information

In this paper, we propose a novel equivalence between probability theory...
research
04/01/2023

JacobiNeRF: NeRF Shaping with Mutual Information Gradients

We propose a method that trains a neural radiance field (NeRF) to encode...
research
03/23/2021

Pairwise Adjusted Mutual Information

A well-known metric for quantifying the similarity between two clusterin...
research
10/09/2019

On the Possibility of Rewarding Structure Learning Agents: Mutual Information on Linguistic Random Sets

We present a first attempt to elucidate an Information-Theoretic approac...

Please sign up or login with your details

Forgot password? Click here to reset