ITLGSep 4, 2024

Gaussian Rate-Distortion-Perception Coding and Entropy-Constrained Scalar Quantization

arXiv:2409.02388v18 citationsh-index: 6
Originality Synthesis-oriented
AI Analysis

This work provides theoretical analysis of fundamental limits in rate-distortion-perception coding for the Gaussian case, which is incremental to existing information theory research.

This paper investigates bounds on the Gaussian distortion-rate-perception function for two perception measures (Kullback-Leibler divergence and squared Wasserstein-2 distance), showing these bounds are nondegenerate and establishing an improved lower bound for the Wasserstein-2 case, while revealing that all bounds are generally not tight in the weak perception constraint regime.

This paper investigates the best known bounds on the quadratic Gaussian distortion-rate-perception function with limited common randomness for the Kullback-Leibler divergence-based perception measure, as well as their counterparts for the squared Wasserstein-2 distance-based perception measure, recently established by Xie et al. These bounds are shown to be nondegenerate in the sense that they cannot be deduced from each other via a refined version of Talagrand's transportation inequality. On the other hand, an improved lower bound is established when the perception measure is given by the squared Wasserstein-2 distance. In addition, it is revealed by exploiting the connection between rate-distortion-perception coding and entropy-constrained scalar quantization that all the aforementioned bounds are generally not tight in the weak perception constraint regime.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes