DeepSAQ: Deep Learning-Driven Sensitivity-Aware Quantization for MMSE MIMO Detection

doi:10.1109/LWC.2025.3627417

DeepSAQ: Deep Learning-Driven Sensitivity-Aware Quantization for MMSE MIMO Detection

2026-01-01

0

PRE

AI

Muhammad, Mohd Khairul Idlan

DOI：10.1109/LWC.2025.3627417

Original

Original request for help

Save

Abstract

En 中文

Hardware-efficient quantization strategies are imperative for massive MIMO detectors. However, conventional methods such as unified quantization and manual tuning respectively suffer from bitwidth redundancy and prohibitive exploration overhead. To address these challenges, this letter proposes a deep learning-driven sensitivity-aware quantization (DeepSAQ) framework, which includes: 1) A gradient-driven framework with a Bayesian optimized loss function to minimize fractional bitwidths; 2) Sensitivity-aware tuning to compress the fractional bitwidth redundancy; 3) Range-extended integral bitwidths to further improve the quantization efficiency. Applying to the unfolded MMSE-wNSA detection, the proposed framework delivers floating-point comparable performance but reduces 50.04% average bitwidths and 50.47% computational complexity compared to the unified quantization. Benchmarking with the recent art, the proposed framework succeeds in squeezing up to 18.32% bitwidths and 21.23% computational complexity in 8 x 128 64-QAM MIMO systems.

Keywords:

Quantization (signal)

Optimization

Sensitivity

Tuning

Redundancy

Training

Probability density function

Computational complexity

Wireless sensor networks

Resource management

Automatic quantization

MIMO detection

gradient descent

MMSE detection

deep learning

DeepSAQ: Deep Learning-Driven Sensitivity-Aware Quantization for MMSE MIMO Detection

Abstract

Journal

Organization