跳到正文
研踪PaperTrail
← 研踪 PaperTrail

arXiv:2611.07946 · v1

Operational Indirect Rate-Distortion Functions for Classification Tasks

首次提交 2026-11-05 20:43
版本更新 2026-11-05 20:43
雷达观测 2026-11-06 11:06
arXiv ↗PDF ↗

摘要

In goal-oriented communications, indirect source coding involves two sources: a semantic source XX and an observation ZZ, which is the only source available at the encoder. In this paper, we consider this framework for classification, where the decoder only needs to reconstruct XX. We argue that the gap between the indirect rate-distortion function and the performance of practical learned coding schemes, such as variational information bottleneck (VIB) and variational autoencoder (VAE) architectures, comes from three effects: the latent representation, the choice of the deep neural network (DNN) architecture and training loss, and whether the encoder is aware of the task. To quantify these effects, we introduce four operational rate-distortion functions that account for the DNN architecture and the training loss, and we establish a hierarchy among them. We then derive these functions for a Gaussian mixture source, where XX is the mixture state. Numerical results, both for the Gaussian mixture and for practical coding schemes on the CIFAR-100 dataset, quantify the rate loss incurred by each effect.

作者备注:8 pages, 4 figures

AI 论文解读

基于摘要 · 非全文审阅

此版本尚未生成 AI 解读。解读由后台任务生成并按论文版本保存,登录后共享已有结果。

版本差异

目前只收录了一个版本。收录下一版后,可以对照标题、作者、分类和摘要。

观测到的版本

相邻记录可能跳过中间版本;首次发现 v2 及以上也会标为版本更新。

v1 · 2026-11-05 20:43 · 最新观测版本

Operational Indirect Rate-Distortion Functions for Classification Tasks

In goal-oriented communications, indirect source coding involves two sources: a semantic source XX and an observation ZZ, which is the only source available at the encoder. In this paper, we consider this framework for classification, where the decoder only needs to reconstruct XX. We argue that the gap between the indirect rate-distortion function and the performance of practical learned coding schemes, such as variational information bottleneck (VIB) and variational autoencoder (VAE) architectures, comes from three effects: the latent representation, the choice of the deep neural network (DNN) architecture and training loss, and whether the encoder is aware of the task. To quantify these effects, we introduce four operational rate-distortion functions that account for the DNN architecture and the training loss, and we establish a hierarchy among them. We then derive these functions for a Gaussian mixture source, where XX is the mixture state. Numerical results, both for the Gaussian mixture and for practical coding schemes on the CIFAR-100 dataset, quantify the rate loss incurred by each effect.

查看此版本解读 →查看此版本原文 ↗