Generalized Nearest Neighbor Decoding: General Input Constellation and a Case Study of Interference Suppression

2024-09-13

arXiv.org

AI Summary

This work addresses the performance bottleneck of generalized nearest-neighbor decoding (GNND) under non-Gaussian inputs—specifically, arbitrary signal constellations—in multi-user uplink interference suppression. We propose a novel symbol-level memoryless precoding and decoding framework. Its core contribution is the first derivation of the optimal criterion for GNND with arbitrary input constellations: conditional moment matching—thereby extending theoretical foundations beyond the classical Gaussian-input assumption. The proposed scheme avoids iterative message passing and remains fully compatible with standard Gaussian-channel decoders. Numerical experiments demonstrate that, in typical uplink scenarios, it achieves rates approaching the channel mutual information—significantly outperforming existing linear receivers such as channel linearization (CL). This provides a practical, low-complexity pathway toward capacity逼近 under finite constellations.

Technology Category

• Cognitive Modeling & Cognitive Systems: Neural Spike Coding
• Search and Optimization: Non-convex Optimization
• Machine Learning: Information Theory

Application Category

• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation
• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

In this work, generalized nearest neighbor decoding (GNND), a recently proposed receiver architecture, is studied for channels under general input constellations, and multiuser uplink interference suppression is employed as a case study for demonstrating its potential. In essence, GNND generalizes the wellknown nearest neighbor decoding, by introducing a symbol-level memoryless processing step, which can be rendered seamlessly compatible with Gaussian channel-based decoders. First, criteria of the optimal GNND are derived for general input constellations, expressed in the form of conditional moments matching, thereby generalizing the prior work which has been confined to Gaussian input. Then, the optimal GNND is applied to the use case of multiuser uplink, for which the optimal GNND is shown to be capable of achieving information rates nearly identical to the channel mutual information. By contrast, the commonly used channel linearization (CL) approach incurs a noticeable rate loss. A coded modulation scheme is subsequently developed, aiming at implementing GNND using off-the-shelf channel codes, without requiring iterative message passing between demodulator and decoder. Through numerical experiments it is validated that the developed scheme significantly outperforms the CL-based scheme.

Problem

• Generalized nearest neighbor decoding for general input constellations
• Optimal GNND criteria derived via conditional moments matching
• GNND outperforms linearization in multiuser uplink interference suppression

Innovation

• GNND generalizes nearest neighbor decoding
• Optimal GNND matches conditional moments
• GNND outperforms linearization without iteration