Connections Between Adaptive Control and Optimization in Machine Learning
Optimization and Control
2020-04-17 v1 Machine Learning
Systems and Control
Abstract
This paper demonstrates many immediate connections between adaptive control and optimization methods commonly employed in machine learning. Starting from common output error formulations, similarities in update law modifications are examined. Concepts in stability, performance, and learning, common to both fields are then discussed. Building on the similarities in update laws and common concepts, new intersections and opportunities for improved algorithm analysis are provided. In particular, a specific problem related to higher order learning is solved through insights obtained from these intersections.
Cite
@article{arxiv.1904.05856,
title = {Connections Between Adaptive Control and Optimization in Machine Learning},
author = {Joseph E. Gaudio and Travis E. Gibson and Anuradha M. Annaswamy and Michael A. Bolender and Eugene Lavretsky},
journal= {arXiv preprint arXiv:1904.05856},
year = {2020}
}
Comments
18 pages