Computing Capacity-Cost Functions for Continuous Channels in Wasserstein Space

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Li, Xinyang, Andrei, Vlad C., Mönich, Ullrich J., Liu, Fan, Boche, Holger
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916637881401344
author Li, Xinyang
Andrei, Vlad C.
Mönich, Ullrich J.
Liu, Fan
Boche, Holger
author_facet Li, Xinyang
Andrei, Vlad C.
Mönich, Ullrich J.
Liu, Fan
Boche, Holger
contents This paper investigates the problem of computing capacity-cost (C-C) functions for continuous channels. Motivated by the Kullback-Leibler divergence (KLD) proximal reformulation of the classical Blahut-Arimoto (BA) algorithm, the Wasserstein distance is introduced to the proximal term for the continuous case, resulting in an iterative algorithm related to the Wasserstein gradient descent. Practical implementation involves moving particles along the negative gradient direction of the objective function's first variation in the Wasserstein space and approximating integrals by the importance sampling (IS) technique. Such formulation is also applied to the rate-distortion (R-D) function for continuous source spaces and thus provides a unified computation framework for both problems.
format Preprint
id arxiv_https___arxiv_org_abs_2501_10670
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Computing Capacity-Cost Functions for Continuous Channels in Wasserstein Space
Li, Xinyang
Andrei, Vlad C.
Mönich, Ullrich J.
Liu, Fan
Boche, Holger
Information Theory
Signal Processing
Optimization and Control
This paper investigates the problem of computing capacity-cost (C-C) functions for continuous channels. Motivated by the Kullback-Leibler divergence (KLD) proximal reformulation of the classical Blahut-Arimoto (BA) algorithm, the Wasserstein distance is introduced to the proximal term for the continuous case, resulting in an iterative algorithm related to the Wasserstein gradient descent. Practical implementation involves moving particles along the negative gradient direction of the objective function's first variation in the Wasserstein space and approximating integrals by the importance sampling (IS) technique. Such formulation is also applied to the rate-distortion (R-D) function for continuous source spaces and thus provides a unified computation framework for both problems.
title Computing Capacity-Cost Functions for Continuous Channels in Wasserstein Space
topic Information Theory
Signal Processing
Optimization and Control
url https://arxiv.org/abs/2501.10670