On Convergence of Discrete Schemes for Computing the Rate-Distortion Function of Continuous Source
Lingyi Chen, Shitong Wu, Tsinghua University, China; Wenyi Zhang, University of Science and Technology of China, China; Huihui Wu, University of Electronic Science and Technology of China, China; Hao Wu, Tsinghua University, China
Session:
Rate Distortion Theory 1
Track:
9: Shannon Theory
Location:
Omikron II
Presentation Time:
Mon, 8 Jul, 14:55 - 15:15
Session Chair:
Wenyi Zhang,
Abstract
THIS PAPER IS ELIGIBLE FOR THE STUDENT PAPER AWARD. Computing the rate-distortion function for continuous sources is commonly regarded as a standard continuous optimization problem. When numerically addressing this problem, a typical approach involves discretizing the source space and subsequently solving the associated discrete problem. However, existing literature has predominantly concentrated on the convergence analysis of solving discrete problems, usually neglecting the convergence relationship between the original continuous optimization and its associated discrete counterpart. This neglect is not rigorous, since the solution of a discrete problem does not necessarily imply convergence to the solution of the original continuous problem, especially for non-linear problems. To address this gap, our study employs rigorous mathematical analysis, which constructs a series of finite-dimensional spaces approximating the infinite-dimensional space of the probability measure, establishing that solutions from discrete schemes converge to those from the continuous problems.