Robust MIMO Detection using Hypernetworks with Learned Regularizers
This work addresses the challenge of designing generic neural network detectors for MIMO systems, which is an incremental improvement for wireless communication applications.
The paper tackles the NP-hard problem of optimal symbol detection in MIMO systems by proposing a hypernetwork-based method that balances symbol error rate performance and channel generality, showing high performance for prespecified channels and good generalization to channels from a specific distribution.
Optimal symbol detection in multiple-input multiple-output (MIMO) systems is known to be an NP-hard problem. Recently, there has been a growing interest to get reasonably close to the optimal solution using neural networks while keeping the computational complexity in check. However, existing work based on deep learning shows that it is difficult to design a generic network that works well for a variety of channels. In this work, we propose a method that tries to strike a balance between symbol error rate (SER) performance and generality of channels. Our method is based on hypernetworks that generate the parameters of a neural network-based detector that works well on a specific channel. We propose a general framework by regularizing the training of the hypernetwork with some pre-trained instances of the channel-specific method. Through numerical experiments, we show that our proposed method yields high performance for a set of prespecified channel realizations while generalizing well to all channels drawn from a specific distribution.