Construction of Bayesian deformable models via a stochastic approximation algorithm: a convergence study

DOI10.3150/09-BEJ229zbMATH Open1220.62101arXiv0706.0787MaRDI QIDQ637075FDOQ637075

Authors: Stéphanie Allassonnière, Estelle Kuhn, Alain Trouvé 

Publication date: 2 September 2011

Published in: Bernoulli (Search for Journal in Brave)

Abstract: The problem of the definition and the estimation of generative models based on deformable templates from raw data is of particular importance for modelling non aligned data affected by various types of geometrical variability. This is especially true in shape modelling in the computer vision community or in probabilistic atlas building for Computational Anatomy (CA). A first coherent statistical framework modelling the geometrical variability as hidden variables has been given by Allassonni`ere, Amit and Trouv'e (JRSS 2006). Setting the problem in a Bayesian context they proved the consistency of the MAP estimator and provided a simple iterative deterministic algorithm with an EM flavour leading to some reasonable approximations of the MAP estimator under low noise conditions. In this paper we present a stochastic algorithm for approximating the MAP estimator in the spirit of the SAEM algorithm. We prove its convergence to a critical point of the observed likelihood with an illustration on images of handwritten digits.

Full work available at URL: https://arxiv.org/abs/0706.0787

Recommendations

• scientific article; zbMATH DE number 6458272
• scientific article; zbMATH DE number 1974093
• Convergent stochastic expectation maximization algorithm with efficient sampling in high dimension. Application to deformable template model estimation
• Bayesian analysis of deformed tessellation models
• Theory and practice of hierarchical data-driven descent for optimal deformation estimation
• Bayesian methods for the shape invariant model

zbMATH Keywords

Bayesian modelingstochastic approximation algorithmsshape statisticsMAP estimationnon-rigid deformable templates

Mathematics Subject Classification ID

Bayesian inference (62F15) Image analysis in multivariate analysis (62H35) Stochastic approximation (62L20)

Cites Work

• Title not available (Why is that?)
• Convergence of a stochastic approximation version of the EM algorithm
• Stability of Stochastic Approximation under Verifiable Conditions
• Markov chains and stochastic stability
• On the ergodicity properties of some adaptive MCMC algorithms
• A penalized likelihood approach to image warping. (With discussion).
• Title not available (Why is that?)
• Computational anatomy: an emerging discipline
• Variational methods for multimodal image matching
• Quantitative bounds on convergence of time-inhomogeneous Markov chains
• Coupling a stochastic approximation version of EM with an MCMC procedure
• Convergence properties of the Gibbs sampler for perturbations of Gaussians

Cited In (31)

• Estimation in shape mixtures of skew-normal linear regression models via ECM coupled with Gibbs sampling
• A new class of stochastic EM algorithms. Escaping local maxima and handling intractable sampling
• Template estimation in computational anatomy: Fréchet means top and quotient spaces are not consistent
• A stochastic approximation ECME algorithm to semi-parametric scale mixtures of centred skew normal regression models
• A sub-Riemannian modular framework for diffeomorphism-based analysis of shape ensembles
• High-frequency volatility modeling: a Markov-switching autoregressive conditional intensity model
• How to calculate the barycenter of a weighted graph
• A reparameterisation based approach to geodesic constrained solvers for curve matching
• A coherent framework for learning spatiotemporal piecewise-geodesic trajectories from longitudinal manifold-valued data
• Stochastic algorithm for Bayesian mixture effect template estimation
• A Bayesian mixed-effects model to learn trajectories of changes from repeated manifold-valued observations
• Assessing the correlation structure in cow udder quarter infection times through extensions of the correlated frailty model
• Bayesian analysis of deformed tessellation models
• A stochastic algorithm for probabilistic independent component analysis
• Bayesian mixed effect atlas estimation with a diffeomorphic deformation model
• Bayesian methods for the shape invariant model
• An improved SAEM algorithm for maximum likelihood estimation in mixtures of non linear mixed effects models
• On a convergent stochastic estimation algorithm for frailty models
• Influence diagnostics in spatial models with censored response
• Properties of the stochastic approximation EM algorithm with mini-batch sampling
• A mixed stochastic approximation EM (MSAEM) algorithm for the estimation of the four-parameter normal ogive model
• Statistical models for deformable templates in image and shape analysis
• A CONSISTENT FRAMEWORK FOR A STATISTICAL ANALYSIS OF SURFACES BASED ON GENERALIZED STOCHASTIC PROCESSES
• Learning the clustering of longitudinal shape data sets into a mixture of independent or branching trajectories
• Sparse adaptive parameterization of variability in image ensembles
• On the convergence of stochastic approximations under a subgeometric ergodic Markov dynamic
• Quantile regression for nonlinear mixed effects models: a likelihood based perspective
• Bayesian inference of whole-organ deformation dynamics from limited space-time point data
• On the curved exponential family in the stochastic approximation expectation maximization algorithm
• Title not available (Why is that?)
• Convergent stochastic expectation maximization algorithm with efficient sampling in high dimension. Application to deformable template model estimation

This page was built for publication: Construction of Bayesian deformable models via a stochastic approximation algorithm: a convergence study

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q637075)