English

Riemannian stochastic approximation algorithms

Optimization and Control 2022-12-29 v3 Machine Learning Dynamical Systems

Abstract

We examine a wide class of stochastic approximation algorithms for solving (stochastic) nonlinear problems on Riemannian manifolds. Such algorithms arise naturally in the study of Riemannian optimization, game theory and optimal transport, but their behavior is much less understood compared to the Euclidean case because of the lack of a global linear structure on the manifold. We overcome this difficulty by introducing a suitable Fermi coordinate frame which allows us to map the asymptotic behavior of the Riemannian Robbins-Monro (RRM) algorithms under study to that of an associated deterministic dynamical system. In so doing, we provide a general template of almost sure convergence results that mirrors and extends the existing theory for Euclidean Robbins-Monro schemes, despite the significant complications that arise due to the curvature and topology of the underlying manifold. We showcase the flexibility of the proposed framework by applying it to a range of retraction-based variants of the popular optimistic / extra-gradient methods for solving minimization problems and games, and we provide a unified treatment for their convergence.

Keywords

Cite

@article{arxiv.2206.06795,
  title  = {Riemannian stochastic approximation algorithms},
  author = {Mohammad Reza Karimi and Ya-Ping Hsieh and Panayotis Mertikopoulos and Andreas Krause},
  journal= {arXiv preprint arXiv:2206.06795},
  year   = {2022}
}

Comments

33 pages, 2 figures; a one-page abstract of this paper was presented in COLT 2022

R2 v1 2026-06-24T11:50:40.194Z