A Massive MIMO Sampling Detection Strategy Based on Denoising Diffusion Model

TL;DR

This paper introduces a novel SVD-free massive MIMO detection strategy using denoising diffusion models, significantly improving performance and complexity trade-offs over existing methods.

Contribution

It proposes the approximate diffusion detection (ADD) scheme that leverages denoising diffusion models to enhance iterative detection without SVD in massive MIMO systems.

Findings

ADD outperforms existing score-based detectors in complexity and performance.

The scheme effectively bypasses SVD, reducing computational burden.

Customized with conjugate gradient descent, it achieves better trade-offs.

Abstract

The Langevin sampling method relies on an accurate score matching while the existing massive multiple-input multiple output (MIMO) Langevin detection involves an inevitable singular value decomposition (SVD) to calculate the posterior score. In this work, a massive MIMO sampling detection strategy that leverages the denoising diffusion model is proposed to narrow the gap between the given iterative detector and the maximum likelihood (ML) detection in an SVD-free manner. Specifically, the proposed score-based sampling detection strategy, denoted as approximate diffusion detection (ADD), is applicable to a wide range of iterative detection methods, and therefore entails a considerable potential in their performance improvement by multiple sampling attempts. On the other hand, the ADD scheme manages to bypass the channel SVD by introducing a reliable iterative detector to produce a sample from the approximate posterior, so that further Langevin sampling is tractable. Customized by the conjugated gradient descent algorithm as an instance, the proposed sampling scheme outperforms the existing score-based detector in terms of a better complexity-performance trade-off.