![[2602.13446] End-to-End NOMA with Perfect and Quantized CSI Over Rayleigh Fading Channels](https://arxiv.org/static/browse/0.3.4/images/arxiv-logo-fb.png){kind=logo}
[2602.13446] End-to-End NOMA with Perfect and Quantized CSI Over Rayleigh Fading Channels
Summary
This paper presents an end-to-end autoencoder framework for downlink non-orthogonal multiple access (NOMA) over Rayleigh fading channels, incorporating both perfect and quantized channel state information (CSI).
Why It Matters
The research addresses a significant gap in wireless communication by developing a framework that directly integrates the wireless channel into the training and inference processes. This can enhance the performance of NOMA systems in real-world scenarios where channel conditions are less than ideal, making it relevant for future wireless network designs.
Key Takeaways
- The proposed autoencoder framework effectively learns interference-aware signaling strategies.
- Incorporating quantized CSI improves the bit error rate (BER) performance compared to uniform quantization.
- The framework outperforms existing analytical NOMA schemes under perfect CSI conditions.
- Direct training over Rayleigh fading channels enhances robustness in practical applications.
- This research paves the way for deploying NOMA in environments with realistic CSI constraints.
Computer Science > Information Theory arXiv:2602.13446 (cs) [Submitted on 13 Feb 2026] Title:End-to-End NOMA with Perfect and Quantized CSI Over Rayleigh Fading Channels Authors:Selma Benouadah, Mojtaba Vaezi, Ruizhan Shen, Hamid Jafarkhani View a PDF of the paper titled End-to-End NOMA with Perfect and Quantized CSI Over Rayleigh Fading Channels, by Selma Benouadah and 3 other authors View PDF HTML (experimental) Abstract:An end-to-end autoencoder (AE) framework is developed for downlink non-orthogonal multiple access (NOMA) over Rayleigh fading channels, which learns interference-aware and channel-adaptive super-constellations. While existing works either assume additive white Gaussian noise channels or treat fading channels without a fully end-to-end learning approach, our framework directly embeds the wireless channel into both training and inference. To account for practical channel state information (CSI), we further incorporate limited feedback via both uniform and Lloyd-Max quantization of channel gains and analyze their impact on AE training and bit error rate (BER) performance. Simulation results show that, with perfect CSI, the proposed AE outperforms the existing analytical NOMA schemes. In addition, Lloyd-Max quantization achieves superior BER performance compared to uniform quantization. These results demonstrate that end-to-end AEs trained directly over Rayleigh fading can effectively learn robust, interference-aware signaling strategies, paving the way for ...
