English

From Contraction Theory to Fixed Point Algorithms on Riemannian and Non-Euclidean Spaces

Optimization and Control 2022-07-19 v1 Systems and Control Systems and Control

Abstract

The design of fixed point algorithms is at the heart of monotone operator theory, convex analysis, and of many modern optimization problems arising in machine learning and control. This tutorial reviews recent advances in understanding the relationship between Demidovich conditions, one-sided Lipschitz conditions, and contractivity theorems. We review the standard contraction theory on Euclidean spaces as well as little-known results for Riemannian manifolds. Special emphasis is placed on the setting of non-Euclidean norms and the recently introduced weak pairings for the 1\ell_1 and \ell_\infty norms. We highlight recent results on explicit and implicit fixed point schemes for non-Euclidean contracting systems.

Keywords

Cite

@article{arxiv.2110.03623,
  title  = {From Contraction Theory to Fixed Point Algorithms on Riemannian and Non-Euclidean Spaces},
  author = {Francesco Bullo and Pedro Cisneros-Velarde and Alexander Davydov and Saber Jafarpour},
  journal= {arXiv preprint arXiv:2110.03623},
  year   = {2022}
}

Comments

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