GD4: Graph-based Discrete Denoising Diffusion for MIMO Detection

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Lu, Qincheng, Luan, Sitao, Chang, Xiao-Wen
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914524232155136
author Lu, Qincheng
Luan, Sitao
Chang, Xiao-Wen
author_facet Lu, Qincheng
Luan, Sitao
Chang, Xiao-Wen
contents In wireless communications, recovering the optimal solution to the multiple-input multiple-output (MIMO) detection problem is NP-hard. Obtaining high-quality suboptimal solutions with a favorable performance-complexity trade-off is particularly challenging in under-determined systems with $N_t$ transmit antennas and $N_r < N_t$ receive antennas. Recent diffusion-based MIMO detectors have shown promise, but they require extensive sampling iterations at inference time, and their performance degrades in under-determined scenarios. We propose GD4, a graph-based discrete denoising diffusion method for MIMO detection. Unlike existing diffusion-based detectors that operate in a continuous relaxed space, GD4 performs denoising directly in the discrete symbol space and enables fast inference with one or a few denoising evaluations. Numerical results show that, under a similar inference-time compute budget, GD4 produces higher-quality suboptimal solutions than existing diffusion-based detectors and some widely used classical baseline including box-constrained Babai point and the $K$-best box-constrained randomized Klein-Babai point in both under-determined and overdetermined settings.
format Preprint
id arxiv_https___arxiv_org_abs_2605_00423
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle GD4: Graph-based Discrete Denoising Diffusion for MIMO Detection
Lu, Qincheng
Luan, Sitao
Chang, Xiao-Wen
Machine Learning
In wireless communications, recovering the optimal solution to the multiple-input multiple-output (MIMO) detection problem is NP-hard. Obtaining high-quality suboptimal solutions with a favorable performance-complexity trade-off is particularly challenging in under-determined systems with $N_t$ transmit antennas and $N_r < N_t$ receive antennas. Recent diffusion-based MIMO detectors have shown promise, but they require extensive sampling iterations at inference time, and their performance degrades in under-determined scenarios. We propose GD4, a graph-based discrete denoising diffusion method for MIMO detection. Unlike existing diffusion-based detectors that operate in a continuous relaxed space, GD4 performs denoising directly in the discrete symbol space and enables fast inference with one or a few denoising evaluations. Numerical results show that, under a similar inference-time compute budget, GD4 produces higher-quality suboptimal solutions than existing diffusion-based detectors and some widely used classical baseline including box-constrained Babai point and the $K$-best box-constrained randomized Klein-Babai point in both under-determined and overdetermined settings.
title GD4: Graph-based Discrete Denoising Diffusion for MIMO Detection
topic Machine Learning
url https://arxiv.org/abs/2605.00423