Learned Conjugate Gradient Descent Network for Massive MIMO Detection

Abstract

In this work, we consider the use of model-driven deep learning techniques for massive multiple-input multiple-output (MIMO) detection. Compared with conventional MIMO systems, massive MIMO promises improved spectral efficiency, coverage and range. Unfortunately, these benefits are coming at the cost of significantly increased computational complexity. To reduce the complexity of signal detection and guarantee the performance, we present a learned conjugate gradient descent network (LcgNet), which is constructed by unfolding the iterative conjugate gradient descent (CG) detector. In the proposed network, instead of calculating the exact values of the scalar step-sizes, we explicitly learn their universal values. Also, we can enhance the proposed network by augmenting the dimensions of these step-sizes. Furthermore, in order to reduce the memory costs, a novel quantized LcgNet is proposed, where a low-resolution nonuniform quantizer is integrated into the LcgNet to smartly quantize the aforementioned step-sizes. The quantizer is based on a specially designed soft staircase function with learnable parameters to adjust its shape. Meanwhile, due to fact that the number of learnable parameters is limited, the proposed networks are easy and fast to train. Numerical results demonstrate that the proposed network can achieve promising performance with much lower complexity.

arXiv commentPart of this work has been accepted by IEEE ICC 2020

References in corpus (15)

• Adam: A Method for Stochastic Optimization
• Massive MIMO for Next Generation Wireless Systems
• Scaling up MIMO: Opportunities and Challenges with Very Large Arrays
• Learning to Optimize: Training Deep Neural Networks for Wireless Resource Management
• Deep Learning-Based Communication Over the Air
• Fifty Years of MIMO Detection: The Road to Large-Scale MIMOs
• Learning to Detect
• AMP-Inspired Deep Networks for Sparse Linear Inverse Problems
• Large-Scale MIMO Detection for 3GPP LTE: Algorithms and FPGA Implementations
• Deep Unfolding: Model-Based Inspiration of Novel Deep Architectures
• Conjugate Gradient-based Soft-Output Detection and Precoding in Massive MIMO Systems
• Learning optimal nonlinearities for iterative thresholding algorithms
• On Deep Learning-Based Channel Decoding
• Improving Massive MIMO Belief Propagation Detector with Deep Neural Network
• Joint Quantizer Optimization based on Neural Quantizer for Sum-Product Decoder

Cited by in corpus (9)

• Model-Driven Deep Learning for MIMO Detection
• Intelligent Reflecting Surface Enhanced Wireless Network: Two-timescale Beamforming Optimization
• Application of Deep Learning to Sphere Decoding for Large MIMO Systems
• A Variational Bayesian Inference-Inspired Unrolled Deep Network for MIMO Detection
• Channel Estimation for IRS-aided Multiuser Communications with Reduced Error Propagation
• ADMM-based Decoder for Binary Linear Codes Aided by Deep Learning
• Green DetNet: Computation and Memory efficient DetNet using Smart Compression and Training
• Learning to Search for MIMO Detection
• A Low-Complexity ADMM-based Massive MIMO Detectors via Deep Neural Networks