Robust Distributed Compression with Learned Heegard-Berger Scheme
Abstract
We consider lossy compression of an information source when decoder-only side information may be absent. This setup, also referred to as the Heegard-Berger or Kaspi problem, is a special case of robust distributed source coding. Building upon previous works on neural network-based distributed compressors developed for the decoder-only side information (Wyner-Ziv) case, we propose learning-based schemes that are amenable to the availability of side information. We find that our learned compressors mimic the achievability part of the Heegard-Berger theorem and yield interpretable results operating close to information-theoretic bounds. Depending on the availability of the side information, our neural compressors recover characteristics of the point-to-point (i.e., with no side information) and the Wyner-Ziv coding strategies that include binning in the source space, although no structure exploiting knowledge of the source and side information was imposed into the design.
Cite
@article{arxiv.2403.08411,
title = {Robust Distributed Compression with Learned Heegard-Berger Scheme},
author = {Eyyup Tasci and Ezgi Ozyilkan and Oguzhan Kubilay Ulger and Elza Erkip},
journal= {arXiv preprint arXiv:2403.08411},
year = {2024}
}