Lossy Joint Source-Channel Coding over Unknown Channels
Abstract
We analyze the performance of joint source-channel codes in an unknown-channel framework, where the true channel is unknown but the source distribution is known. We derive achievability bounds for a family of mismatched-design joint source-channel codes constructed for a design channel QY|X and operated over a possibly different true channel PY|X. Our one-shot achievability bound allows for standard Borel alphabets for the source, reproduction, channel input and channel output. The subsequent block coding result based on the normal approximation applies to stationary memoryless sources and memoryless, possibly nonstationary channels under regularity and moment conditions. The achievability bound is given in terms of the rate-distortion and rate-dispersion functions, as well as two channel-dependent quantities that we call the mismatched-design rate and mismatched-design rate-dispersion. We use a family of Gibbs posteriors parameterized by a single scalar as decoder-side kernels, and the envelope of the corresponding achievable rates recovers the generalized mutual information. In the stationary matched setting covered by our assumptions, our result recovers the achievability part of Kostina and Verdú's 2013 Gaussian approximation result and improves its third-order term. We also formalize a notion of a second-order universal family of source-channel codes under which there is no first- or second-order asymptotic penalty. We then construct two channel-blind families of source-channel codes: one that is second-order universal over a regular class of nonstationary block erasure channels and another that is second-order universal over stationary Gaussian channels. Our code construction uses Poisson functional representations of suitable conditional probability measures to produce the encoder and decoder outputs.
Related
- Joint Source-Channel Coding of Gaussian Sources over Block Erasure Channels: Nonasymptotic Bounds and Channel-Uniform Normal Approximations
- Secure Joint Source-Channel Coding of Multimodal Semantic Sources
- Domain-Adaptive Deep Joint Source-Channel Coding for Image Classification
- Polar Complexity: A New Descriptive Complexity with Applications to Source and Joint Source-Channel Coding
- OSD-JSCC: Neural Joint Source-Channel Coding with One-Step Diffusion
BibTeX
@misc{mahmood2026lossy,
title = {{Lossy Joint Source-Channel Coding over Unknown Channels}},
author = {Adeel Mahmood and Harish Viswanathan and Jinfeng Du},
howpublished = {arXiv},
year = {2026},
month = sep,
doi = {10.48550/arxiv.2606.07933},
eprint = {2606.07933},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2606.07933},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - Lossy Joint Source-Channel Coding over Unknown Channels
AU - Adeel Mahmood
AU - Harish Viswanathan
AU - Jinfeng Du
PY - 2026
DA - 2026/09/02
PB - arXiv
DO - 10.48550/arxiv.2606.07933
UR - https://arxiv.org/abs/2606.07933
AB - We analyze the performance of joint source-channel codes in an unknown-channel framework, where the true channel is unknown but the source distribution is known. We derive achievability bounds for a family of mismatched-design joint source-channel codes constructed for a design channel Q_Y|X and operated over a possibly different true channel P_Y|X. Our one-shot achievability bound allows for standard Borel alphabets for the source, reproduction, channel input and channel output. The subsequent block coding result based on the normal approximation applies to stationary memoryless sources and memoryless, possibly nonstationary channels under regularity and moment conditions. The achievability bound is given in terms of the rate-distortion and rate-dispersion functions, as well as two channel-dependent quantities that we call the mismatched-design rate and mismatched-design rate-dispersion. We use a family of Gibbs posteriors parameterized by a single scalar as decoder-side kernels, and the envelope of the corresponding achievable rates recovers the generalized mutual information. In the stationary matched setting covered by our assumptions, our result recovers the achievability part of Kostina and Verdú's 2013 Gaussian approximation result and improves its third-order term. We also formalize a notion of a second-order universal family of source-channel codes under which there is no first- or second-order asymptotic penalty. We then construct two channel-blind families of source-channel codes: one that is second-order universal over a regular class of nonstationary block erasure channels and another that is second-order universal over stationary Gaussian channels. Our code construction uses Poisson functional representations of suitable conditional probability measures to produce the encoder and decoder outputs.
ER -