A stochastic algorithm finding generalized means on compact manifolds

DOI10.1016/j.spa.2014.05.011zbMath1314.60041arXiv1301.7156OpenAlexW2092133847MaRDI QIDQ404139

Laurent Miclo, Marc Arnaudon

Publication date: 4 September 2014

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

Full work available at URL: https://arxiv.org/abs/1301.7156

zbMATH Keywords

simulated annealinghomogenizationstochastic algorithmsGibbs measuresinstantaneous invariant measuresintrinsic meansprobability measures on compact Riemannian manifoldsspectral gap at small temperatureintrinsic \(p\)-means

Mathematics Subject Classification ID

Probability measures on topological spaces (60B05) Geometric probability and stochastic geometry (60D05) Brownian motion (60J65) Applications of stochastic analysis (to PDEs, etc.) (60H30) Integration on manifolds; measures on manifolds (58C35) Ergodic theorems, spectral theory, Markov operators (37A30) Methods of global Riemannian geometry, including PDE methods; curvature restrictions (53C21) Integro-differential operators (47G20)

Related Items

A stochastic algorithm finding generalized means on compact manifolds, Regularizing Orientation Estimation in Cryogenic Electron Microscopy Three-Dimensional Map Refinement through Measure-Based Lifting over Riemannian Manifolds, Warped Riemannian Metrics for Location-Scale Models, How to Calculate the Barycenter of a Weighted Graph, An algorithm for computing Fréchet means on the sphere

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Efficient and fast estimation of the geometric median in Hilbert spaces with an averaged stochastic gradient algorithm
• A stochastic algorithm finding generalized means on compact manifolds
• Stochastic algorithms for computing means of probability measures
• On approximating the Riemannian 1-center
• Intrinsic statistics on Riemannian manifolds: Basic tools for geometric measurements
• Asymptotics of the spectral gap with applications to the theory of simulated annealing
• Laplace's method revisited: Weak convergence of probability measures
• Recuit simulé partiel. (Partial simulated annealing)
• A study of subadmissible simulated annealing algorithms
• Newton's method, zeroes of vector fields, and the Riemannian center of mass
• Remarks on the ergodicity of simulated annealing algorithms on a graph
• Intrinsic means on the circle: uniqueness, locus and asymptotics
• On the Convergence of Gradient Descent for Finding the Riemannian Center of Mass
• Riemannian median and its estimation
• Recuit simulésans potentiel sur une variétériemannienne compacte
• Estimates of derivatives of the heat kernel on a compact Riemannian manifold
• Direction Estimation by Minimum Squared Arc Length
• Estimation of Riemannian Barycentres
• Medians and means in Finsler geometry
• Means in complete manifolds: uniqueness and approximation
• Stochastic Gradient Descent on Riemannian Manifolds
• Necessary and sufficient condition for the existence of a Fréchet mean on the circle
• On the convergence of some Procrustean averaging algorithms
• Riemannian geometry and geometric analysis