Variational Autoencoders for Precoding Matrices with High Spectral Efficiency
This work addresses the need for efficient precoding in wireless communication, but it is incremental as it applies existing VAE methods to a specific domain.
The paper tackles the problem of generating high spectral efficiency precoding matrices for MIMO wireless systems using variational autoencoders, achieving minimal quality loss compared to optimal precoding with a computationally efficient algorithm.
Neural networks are used for channel decoding, channel detection, channel evaluation, and resource management in multi-input and multi-output (MIMO) wireless communication systems. In this paper, we consider the problem of finding precoding matrices with high spectral efficiency (SE) using variational autoencoder (VAE). We propose a computationally efficient algorithm for sampling precoding matrices with minimal loss of quality compared to the optimal precoding. In addition to VAE, we use the conditional variational autoencoder (CVAE) to build a unified generative model. Both of these methods are able to reconstruct the distribution of precoding matrices of high SE by sampling latent variables. This distribution obtained using VAE and CVAE methods is described in the literature for the first time.