Skip to content
DraconiticResearch
Search Sources API
203,234 studies31 sourcesUpdated 38 min ago
PreprintCC BY 4.0arXiv

MAP-Based Task-Oriented Precoding for Multiuser Communication

  • Mohammad Javad Ahmadi
  • Zhentian Zhang
  • Rafael F. Schaefer
  • H. Vincent Poor
Open at sourcePDFDOICite

Abstract

We propose a task-oriented multiuser wireless communication framework for distributed classification based on a MAP-driven system design under wireless channel impairments. \textcolor{black}{By deriving tractable approximations of the MAP error bound}, the proposed approach enables the design of learning-based feature extraction and precoding strategies. Unlike existing approaches that optimize intermediate reconstruction, information-theoretic, or feature-separability objectives, the proposed formulation directly optimizes objectives derived from the MAP decision error, thereby providing a more direct connection to the final classification performance. Simulation results demonstrate that the proposed schemes achieve higher classification accuracy than their counterparts, with lower or comparable computational complexity.

Related

  1. More Interactions Make Communications More Efficient: A Directed Information Bottleneck Approach to Task-Oriented Communication
    Zhirun Zheng, Yiqin Deng, Phone Lin +1
    arXivPreprintCC BY 4.0Full textGeneral mathematicsarXiv
  2. Task-Oriented Quantization for Quadratic Scheduling: Centroid Water-Filling and Power-Diagram Encoders
    Joss Armstrong
    arXivPreprintarXiv licenceFull textGeneral mathematicsarXiv
  3. AI-Native Task-Oriented Semantic Communications over a Relay: Benefits and Vulnerabilities
    Yalin E. Sagduyu, Tugba Erpek, Aylin Yener
    arXivPreprintarXiv licenceFull textGeneral mathematicsarXiv
  4. Benchy: towards a universal language for task-oriented AI benchmarks
    Francis F Daniel, Mauro Ibañez, Francis Perelman +1
    arXivPreprintCC BY 4.0Full textStatisticsarXiv
  5. Task-Oriented Boolean Function Computation: Practical Code Constructions
    Yangshuo He, Guanding Yu, Jingge Zhu
    arXivPreprintCC BY 4.0Full textGeneral mathematicsarXiv

Cite

BibTeXRIS
BibTeX
@misc{ahmadi2026mapbased,
  title = {{MAP-Based Task-Oriented Precoding for Multiuser Communication}},
  author = {Mohammad Javad Ahmadi and Zhentian Zhang and Rafael F. Schaefer and H. Vincent Poor},
  howpublished = {arXiv},
  year = {2026},
  month = aug,
  doi = {10.48550/arxiv.2606.25722},
  eprint = {2606.25722},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2606.25722},
  note = {CC BY 4.0},
}
RIS
TY  - UNPB
TI  - MAP-Based Task-Oriented Precoding for Multiuser Communication
AU  - Mohammad Javad Ahmadi
AU  - Zhentian Zhang
AU  - Rafael F. Schaefer
AU  - H. Vincent Poor
PY  - 2026
DA  - 2026/08/28
PB  - arXiv
DO  - 10.48550/arxiv.2606.25722
UR  - https://arxiv.org/abs/2606.25722
AB  - We propose a task-oriented multiuser wireless communication framework for distributed classification based on a MAP-driven system design under wireless channel impairments. \textcolor{black}{By deriving tractable approximations of the MAP error bound}, the proposed approach enables the design of learning-based feature extraction and precoding strategies. Unlike existing approaches that optimize intermediate reconstruction, information-theoretic, or feature-separability objectives, the proposed formulation directly optimizes objectives derived from the MAP decision error, thereby providing a more direct connection to the final classification performance. Simulation results demonstrate that the proposed schemes achieve higher classification accuracy than their counterparts, with lower or comparable computational complexity.
ER  -