Output-Constrained Lossy Source Coding With Application to Rate-Distortion-Perception Theory

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Xie, Li, Li, Liangyan, Chen, Jun, Zhang, Zhongshan
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913277960781824
author Xie, Li
Li, Liangyan
Chen, Jun
Zhang, Zhongshan
author_facet Xie, Li
Li, Liangyan
Chen, Jun
Zhang, Zhongshan
contents The distortion-rate function of output-constrained lossy source coding with limited common randomness is analyzed for the special case of squared error distortion measure. An explicit expression is obtained when both source and reconstruction distributions are Gaussian. This further leads to a partial characterization of the information-theoretic limit of quadratic Gaussian rate-distortion-perception coding with the perception measure given by Kullback-Leibler divergence or squared quadratic Wasserstein distance.
format Preprint
id arxiv_https___arxiv_org_abs_2403_14849
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Output-Constrained Lossy Source Coding With Application to Rate-Distortion-Perception Theory
Xie, Li
Li, Liangyan
Chen, Jun
Zhang, Zhongshan
Information Theory
Machine Learning
The distortion-rate function of output-constrained lossy source coding with limited common randomness is analyzed for the special case of squared error distortion measure. An explicit expression is obtained when both source and reconstruction distributions are Gaussian. This further leads to a partial characterization of the information-theoretic limit of quadratic Gaussian rate-distortion-perception coding with the perception measure given by Kullback-Leibler divergence or squared quadratic Wasserstein distance.
title Output-Constrained Lossy Source Coding With Application to Rate-Distortion-Perception Theory
topic Information Theory
Machine Learning
url https://arxiv.org/abs/2403.14849