Stochastic algorithms for computing means of probability measures

DOI10.1016/J.SPA.2011.12.011MaRDI QIDQ424479zbMATH OpenOpenAlexFDO

Authors Marc Arnaudon, Anthony Phan, Le Yang, Clément Dombry

Publication date 1 June 2012

Published in Stochastic Processes and their Applications (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/1106.5106

zbMATH Keywords

Markov chainmeanconvexityRiemannian geometryprobability measureinvariance principlebarycentergeodesic ball

Mathematics Subject Classification ID

Computational methods in Markov chains (60J22) Strong limit theorems (60F15) Discrete-time Markov processes on general state spaces (60J05) Integration on manifolds; measures on manifolds (58C35)

Abstract: Consider a probability measure supported by a regular geodesic ball in a manifold. For any p larger than or equal to 1 we define a stochastic algorithm which converges almost surely to the p-mean of the measure. Assuming furthermore that the functional to minimize is regular around the p-mean, we prove that a natural renormalization of the inhomogeneous Markov chain converges in law into an inhomogeneous diffusion process. We give an explicit expression of this process, as well as its local characteristic.

Recommendations

• Means in complete manifolds: uniqueness and approximation
• scientific article; zbMATH DE number 19577
• On the convergence of markovian stochastic algorithms with rapidly decreasing ergodicity rates

Cites work

• scientific article; zbMATH DE number 3664138 (Why is no real title available?)
• scientific article; zbMATH DE number 19577 (Why is no real title available?)
• Almost sure invariance principle for dynamical systems by spectral methods
• An almost sure invariance principle for stochastic approximation procedures in linear filtering theory
• Analysis of recursive stochastic algorithms
• Analysis of stochastic approximation schemes with discontinuous and dependent forcing terms with applications to data communication algorithms
• Barycenters and martingales on a manifold
• Barycenters of measures transported by stochastic flows
• Convexity and the Hemisphere
• Dependent central limit theorems and invariance principles
• Estimation of Riemannian Barycentres
• On Stochastic Processes Defined by Differential Equations with a Small Parameter
• Probability, Convexity, and Harmonic Maps with Small Image I: Uniqueness and Fine Existence
• Riemannian \(L^{p}\) center of mass: existence, uniqueness, and convexity
• Riemannian center of mass and mollifier smoothing
• Riemannian median and its estimation

Cited in

(15)

• scientific article; zbMATH DE number 7204268 (Why is no real title available?)
• A hyperbolic approach for learning communities on graphs
• Sampling algorithms for estimating the mean of bounded random variables
• Riemannian L^p averaging on Lie group of nonzero quaternions
• Discrete-time gradient flows and law of large numbers in Alexandrov spaces
• Convergence Analysis of Gradient Algorithms on Riemannian Manifolds without Curvature Constraints and Application to Riemannian Mass
• Stochastic algorithms
• A diffusion process associated with Fréchet means
• Efficient and fast estimation of the geometric median in Hilbert spaces with an averaged stochastic gradient algorithm
• Estimating the geometric median in Hilbert spaces with stochastic gradient algorithms: L^p and almost sure rates of convergence
• Riemannian barycentres of Gibbs distributions: new results on concentration and convexity in compact symmetric spaces
• A Robbins-Monro-type algorithm for computing global minimizer of generalized conic functions
• Characterization of barycenters in the Wasserstein space by averaging optimal transport maps
• Rank-preserving geometric means of positive semi-definite matrices
• On the measure of the cut locus of a Fréchet mean

This page was built for publication: Stochastic algorithms for computing means of probability measures

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q424479)