Mapped ADMM: A Robust Algorithm for 1-Bit mMIMO Detection

2026-07-22

AI Summary

This work addresses the insufficient robustness of signal detection in 1-bit massive MIMO systems by proposing a novel detection method based on decentralized support vector machines (SVMs). The approach reformulates the SVM as a consensus optimization problem among multiple classifiers, incorporates constellation-point mapping constraints to ensure valid output symbols, and introduces a Mapped ADMM framework to balance classifier group sizes—thereby maintaining sufficient per-group data while enhancing consensus accuracy. The proposed method significantly outperforms existing practical detection schemes, achieving superior bit error rate performance and enhanced robustness in 1-bit massive MIMO scenarios.

Abstract

Recently, it has been reported that one-bit massive MIMO (mMIMO) detection is equivalent to a binary classification problem that can be solved efficiently using support vector machine (SVM). Inspired by this result, we first reformulate SVM in a decentralized form consisting of multiple classifiers. This enables the use of the consensus alternating direction method of multipliers (CADMM), a technique that can improve robustness and performance through its inherent consensus making. We further update CADMM to output only valid constellation points and achieve significantly improved detection performance. In our method, by changing the size of the grouped classifiers, we balance the number of classifiers for consensus accuracy with sufficient data per group to ensure classifier robustness. Ultimately, we demonstrate that our proposed method significantly outperforms existing practically feasible methods for one-bit mMIMO detection.

Problem

• 1-bit mMIMO
• signal detection
• robustness
• binary classification
• massive MIMO

Innovation

• 1-bit mMIMO
• decentralized SVM
• consensus ADMM
• constellation-constrained detection
• classifier grouping