.png){kind=icon}
Return
DeepSAQ: Deep Learning-Driven Sensitivity-Aware Quantization for MMSE MIMO Detection
.png){kind=icon}
PRE
AI
DOI：10.1109/LWC.2025.3627417.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
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
Journal
I
IF:
5.5
Papers:
824
Citations:
0
Organization
Cited Papers
ShareSaveReLeQ : A Reinforcement Learning Approach for Automatic Deep Quantization of Neural Networks.png)
IEEE Micro
OAAI
IEEE MicroIF0
OAAIShareSaveShareSave
ShareSaveShareSave
View more