Robust MIMO Detection using Hypernetworks with Learned Regularizers

TL;DR

This paper introduces a hypernetwork-based MIMO detection method that balances near-optimal symbol error rates with broad channel generalization, outperforming existing neural network approaches.

Contribution

It presents a novel hypernetwork framework with learned regularizers that adapt to specific channels while maintaining generalization across channel distributions.

Findings

Achieves high SER performance on prespecified channels

Generalizes effectively to new channels from the same distribution

Balances accuracy and computational efficiency

Abstract

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.