Lossy Compression with Universal Distortion

10/13/2021
by   Adeel Mahmood, et al.
0

A novel variant of lossy coding is considered in which the distortion measure is revealed only to the encoder and only at run-time. Two forms of rate redundancy are used to analyze the performance, and achievability results of both a pointwise and minimax nature are demonstrated. One proof uses appropriate quantization of the space of distortion measures while another uses ideas from VC dimension and growth functions. Future research directions pertaining to Rissanen's redundancy result are discussed.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
02/09/2022

Minimax Rate-Distortion

We show the existence of universal, variable-rate rate-distortion codes ...
research
03/07/2022

D-semifaithful codes that are universal over both memoryless sources and distortion measures

We prove the existence of codebooks for d-semifaithful lossy compression...
research
01/17/2019

Double variational principle for mean dimension

We develop a variational principle between mean dimension theory and rat...
research
03/04/2022

Rate-Distortion Theoretic Generalization Bounds for Stochastic Learning Algorithms

Understanding generalization in modern machine learning settings has bee...
research
07/11/2021

On Universal D-Semifaithful Coding for Memoryless Sources with Infinite Alphabets

The problem of variable length and fixed-distortion universal source cod...
research
01/11/2022

Rate Distortion Theory for Descriptive Statistics

Rate distortion theory was developed for optimizing lossy compression of...
research
01/07/2022

The Efficiency of the ANS Entropy Encoding

The Asymmetric Numeral Systems (ANS) is a class of entropy encoders by D...

Please sign up or login with your details

Forgot password? Click here to reset