most citedSemantic Compression with Side Information: A Rate-Distortion Perspective

8 citations · 8 across the 2 of their papers we have counts for

collaborators

6 papers

cs.IT2024

An Expectation-Maximization Relaxed Method for Privacy Funnel

Lingyi Chen, Jiachuan Ye, Shitong Wu +3

The privacy funnel (PF) gives a framework of privacy-preserving data release, where the goal is to release useful data while also limiting the exposure of associated sensitive info…

cs.IT2024

A Double Maximization Approach for Optimizing the LM Rate of Mismatched Decoding

Lingyi Chen, Shitong Wu, Xinwei Li +3

An approach is established for maximizing the Lower bound on the Mismatch capacity (hereafter abbreviated as LM rate), a key performance bound in mismatched decoding, by optimizing…

cs.IT2024

On Convergence of Discrete Schemes for Computing the Rate-Distortion Function of Continuous Source

Lingyi Chen, Shitong Wu, Wenyi Zhang +2

Computing the rate-distortion function for continuous sources is commonly regarded as a standard continuous optimization problem. When numerically addressing this problem, a typica…

cs.IT2023

Information Bottleneck Revisited: Posterior Probability Perspective with Optimal Transport

Lingyi Chen, Shitong Wu, Wenhao Ye +5

Information bottleneck (IB) is a paradigm to extract information in one target random variable from another relevant random variable, which has aroused great interest due to its po…

cs.IT2022

An Optimal Transport Approach to the Computation of the LM Rate

Wenhao Ye, Huihui Wu, Shitong Wu +4

Mismatch capacity characterizes the highest information rate for a channel under a prescribed decoding metric, and is thus a highly relevant fundamental performance metric when dea…

cs.IT20228 cited

Semantic Compression with Side Information: A Rate-Distortion Perspective

Tao Guo, Yizhu Wang, Jie Han +3

We consider the semantic rate-distortion problem motivated by task-oriented video compression. The semantic information corresponding to the task, which is not observable to the en…