English

Contraction-Based Methods for Stable Identification and Robust Machine Learning: a Tutorial

Systems and Control 2021-10-04 v1 Systems and Control Optimization and Control

Abstract

This tutorial paper provides an introduction to recently developed tools for machine learning, especially learning dynamical systems (system identification), with stability and robustness constraints. The main ideas are drawn from contraction analysis and robust control, but adapted to problems in which large-scale models can be learnt with behavioural guarantees. We illustrate the methods with applications in robust image recognition and system identification.

Keywords

Cite

@article{arxiv.2110.00207,
  title  = {Contraction-Based Methods for Stable Identification and Robust Machine Learning: a Tutorial},
  author = {Ian R. Manchester and Max Revay and Ruigang Wang},
  journal= {arXiv preprint arXiv:2110.00207},
  year   = {2021}
}

Comments

Paper in the invited tutorial session "Contraction Theory for Machine Learning" at 60th IEEE Conference on Decision and Control, 2021