Variational Inference Aided Estimation of Time Varying Channels

TL;DR

This paper introduces a novel deep learning architecture called k-MemoryMarkovVAE for improved estimation of time-varying channels by leveraging temporal correlations, outperforming existing memoryless methods.

Contribution

The paper proposes a new DVAE architecture with controllable sparsity and derives a channel estimator that effectively utilizes temporal correlations in time series data.

Findings

k-MMVAE outperforms memoryless ML estimators on simulated channels.

The architecture effectively captures temporal correlations in channel estimation.

Results demonstrate significant improvement over naive extensions of existing methods.

Abstract

One way to improve the estimation of time varying channels is to incorporate knowledge of previous observations. In this context, Dynamical VAEs (DVAEs) build a promising deep learning (DL) framework which is well suited to learn the distribution of time series data. We introduce a new DVAE architecture, called k-MemoryMarkovVAE (k-MMVAE), whose sparsity can be controlled by an additional memory parameter. Following the approach in [1] we derive a k-MMVAE aided channel estimator which takes temporal correlations of successive observations into account. The results are evaluated on simulated channels by QuaDRiGa and show that the k-MMVAE aided channel estimator clearly outperforms other machine learning (ML) aided estimators which are either memoryless or naively extended to time varying channels without major adaptions.