Non-convex optimization in digital pre-distortion of the signal

TL;DR

This paper explores the application of modern non-convex optimization techniques to digital predistortion of OFDM signals using cascade Wiener--Hammerstein models, comparing their effectiveness and behavior.

Contribution

It introduces a framework for applying advanced optimization methods to DPD models and evaluates their convergence and effectiveness in this context.

Findings

Certain optimization methods outperform others in convergence speed

Model properties influence optimization behavior significantly

Insights into the suitability of neural network optimization techniques for DPD

Abstract

In this paper, we give some observation of applying modern optimization methods for functionals describing digital predistortion (DPD) of signals with orthogonal frequency division multiplexing (OFDM) modulation. The considered family of model functionals is determined by the class of cascade Wiener--Hammerstein models, which can be represented as a computational graph consisting of various nonlinear blocks. To assess optimization methods with the best convergence depth and rate as a properties of this models family we multilaterally consider modern techniques used in optimizing neural networks and numerous numerical methods used to optimize non-convex multimodal functions. The research emphasizes the most effective of the considered techniques and describes several useful observations about the model properties and optimization methods behavior.