11 papers
A Survey of Learn-to-Compute Paradigms for Rate-Distortion-Type Problems
Shitong Wu, Sicheng Xu, Lingyi Chen +4
Rate-distortion (RD) theory and its related formulations play a central role in understanding efficient information representation, but computing these quantities remains challengi…
An Optimal Transport-Based Method for Computing LM Rate and Its Convergence Analysis
Shitong Wu, Wenhao Ye, Xinwei Li +4
The mismatch capacity characterizes the highest information rate of the channel under a prescribed decoding metric and serves as a critical performance indicator in numerous practi…
Neural Estimation of the Information Bottleneck Based on a Mapping Approach
Lingyi Chen, Shitong Wu, Sicheng Xu +2
The information bottleneck (IB) method is a technique designed to extract meaningful information related to one random variable from another random variable, and has found extensiv…
Efficient Computation of Marton's Error Exponent via Constraint Decoupling
Jiachuan Ye, Shitong Wu, Lingyi Chen +3
The error exponent in lossy source coding characterizes the asymptotic decay rate of error probability with respect to blocklength. The Marton's error exponent provides the theoret…
Estimating Rate-Distortion Functions Using the Energy-Based Model
Shitong Wu, Sicheng Xu, Lingyi Chen +2
The rate-distortion (RD) theory is one of the key concepts in information theory, providing theoretical limits for compression performance and guiding the source coding design, wit…
RDD Function: A Tradeoff Between Rate and Distortion-in-Distortion
Lingyi Chen, Haoran Tang, Shitong Wu +4
In this paper, we propose a novel function named Rate Distortion-in-Distortion (RDD) function as an extension of the classical rate-distortion (RD) function, where the expected dis…