Convergence Analysis of Riemannian Stochastic Approximation Schemes - Inria - Institut national de recherche en sciences et technologies du numérique Accéder directement au contenu
Pré-Publication, Document De Travail Année : 2020

Convergence Analysis of Riemannian Stochastic Approximation Schemes

Résumé

This paper analyzes the convergence for a large class of Riemannian stochastic approximation (SA) schemes, which aim at tackling stochastic optimization problems. In particular, the recursions we study use either the exponential map of the considered manifold (geodesic schemes) or more general retraction functions (retraction schemes) used as a proxy for the exponential map. Such approximations are of great interest since they are low complexity alternatives to geodesic schemes. Under the assumption that the mean field of the SA is correlated with the gradient of a smooth Lyapunov function (possibly non-convex), we show that the above Riemannian SA schemes find an O(b ∞ + log n/ √ n)-stationary point (in expectation) within O(n) iterations, where b ∞ ≥ 0 is the asymptotic bias. Compared to previous works, the conditions we derive are considerably milder. First, all our analysis are global as we do not assume iterates to be a-priori bounded. Second, we study biased SA schemes. To be more specific, we consider the case where the mean-field function can only be estimated up to a small bias, and/or the case in which the samples are drawn from a controlled Markov chain. Third, the conditions on retractions required to ensure convergence of the related SA schemes are weak and hold for well-known examples. We illustrate our results on three machine learning problems.
Fichier principal
Vignette du fichier
main.pdf (795.99 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-02626383 , version 1 (26-05-2020)
hal-02626383 , version 2 (27-05-2020)

Identifiants

  • HAL Id : hal-02626383 , version 2

Citer

Alain Durmus, Pablo Jiménez, Eric Moulines, Salem Said, Hoi-To Wai. Convergence Analysis of Riemannian Stochastic Approximation Schemes. 2020. ⟨hal-02626383v2⟩
123 Consultations
229 Téléchargements

Partager

Gmail Facebook X LinkedIn More