Model-Aware Rate-Distortion Limits for Task-Oriented Source Coding

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Enttsel, Andriy, Corlay, Vincent
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917273591087104
author Enttsel, Andriy
Corlay, Vincent
author_facet Enttsel, Andriy
Corlay, Vincent
contents Task-Oriented Source Coding (TOSC) has emerged as a paradigm for efficient visual data communication in machine-centric inference systems, where bitrate, latency, and task performance must be jointly optimized under resource constraints. While recent works have proposed rate-distortion bounds for coding for machines, these results often rely on strong assumptions on task identifiability and neglect the impact of deployed task models. In this work, we revisit the fundamental limits of single-TOSC through the lens of indirect rate-distortion theory. We highlight the conditions under which existing rate-distortion bounds are achievable and show their limitations in realistic settings. We then introduce task model-aware rate-distortion bounds that account for task model suboptimality and architectural constraints. Experiments on standard classification benchmarks confirm that current learned TOSC schemes operate far from these limits, highlighting transmitter-side complexity as a key bottleneck.
format Preprint
id arxiv_https___arxiv_org_abs_2602_12866
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Model-Aware Rate-Distortion Limits for Task-Oriented Source Coding
Enttsel, Andriy
Corlay, Vincent
Information Theory
Machine Learning
Image and Video Processing
Signal Processing
Task-Oriented Source Coding (TOSC) has emerged as a paradigm for efficient visual data communication in machine-centric inference systems, where bitrate, latency, and task performance must be jointly optimized under resource constraints. While recent works have proposed rate-distortion bounds for coding for machines, these results often rely on strong assumptions on task identifiability and neglect the impact of deployed task models. In this work, we revisit the fundamental limits of single-TOSC through the lens of indirect rate-distortion theory. We highlight the conditions under which existing rate-distortion bounds are achievable and show their limitations in realistic settings. We then introduce task model-aware rate-distortion bounds that account for task model suboptimality and architectural constraints. Experiments on standard classification benchmarks confirm that current learned TOSC schemes operate far from these limits, highlighting transmitter-side complexity as a key bottleneck.
title Model-Aware Rate-Distortion Limits for Task-Oriented Source Coding
topic Information Theory
Machine Learning
Image and Video Processing
Signal Processing
url https://arxiv.org/abs/2602.12866