Improving the Bootstrap of Blind Equalizers with Variational Autoencoders

TL;DR

This paper investigates how variational autoencoders can enhance the initial convergence of blind equalizers, addressing challenges at critical points and improving bootstrapping performance.

Contribution

It introduces a novel application of variational autoencoders to improve the startup phase of blind equalizers, which was not previously explored.

Findings

VAE-based equalizers outperform traditional methods in bootstrapping.

Analysis reveals advantages of VAE in overcoming startup obstacles.

Experimental results demonstrate improved convergence speed.

Abstract

We evaluate the start-up of blind equalizers at critical working points, analyze the advantages and obstacles of commonly-used algorithms, and demonstrate how the recently-proposed variational autoencoder (VAE) based equalizers can improve bootstrapping.