On the irreducibility and convergence of a class of nonsmooth nonlinear state-space models on manifolds - Inria - Institut national de recherche en sciences et technologies du numérique
Preprints, Working Papers, ... Year : 2024

On the irreducibility and convergence of a class of nonsmooth nonlinear state-space models on manifolds

Abstract

In this paper, we analyze a large class of general nonlinear state-space models on a state-space X, defined by the recursion ϕ k+1 = F (ϕ k , α(ϕ k , U k+1 )), k ∈ N, where F, α are some functions and {U k+1 } k∈N is a sequence of i.i.d. random variables. More precisely, we extend conditions under which this class of Markov chains is irreducible, aperiodic and satisfies important continuity properties, relaxing two key assumptions from prior works. First, the state-space X is supposed to be a smooth manifold instead of an open subset of a Euclidean space. Second, we only suppose that F is locally Lipschitz continuous. We demonstrate the significance of our results through their application to Markov chains underlying optimization algorithms. These schemes belong to the class of evolution strategies with covariance matrix adaptation and step-size adaptation.
Fichier principal
Vignette du fichier
verifiable_conditions_manifolds.pdf (478.73 Ko) Télécharger le fichier
Origin Files produced by the author(s)

Dates and versions

hal-04713677 , version 1 (30-09-2024)

Licence

Identifiers

Cite

Armand Gissler, Alain Durmus, Anne Auger. On the irreducibility and convergence of a class of nonsmooth nonlinear state-space models on manifolds. 2024. ⟨hal-04713677⟩
0 View
0 Download

Altmetric

Share

More