Construction of Bayesian Deformable Models via Stochastic Approximation Algorithm: a Convergence Study
نویسندگان
چکیده
Abstract. The problem of the definition and the estimation of generative models based on deformable templates from raw data is of particular importance for modeling non-aligned data affected by various types of geometrical variability. This is especially true in shape modeling in the computer vision community or in probabilistic atlas building in Computational Anatomy. A first coherent statistical framework modeling the geometrical variability as hidden variables was described by Allassonnière, Amit and Trouvé in [2]. The present paper gives a theoretical proof of convergence of effective stochastic approximation expectation strategies to estimate such models and shows the robustness of this approach against noise through numerical experiments in the context of handwritten digit modeling.
منابع مشابه
Bayesian Deformable Models Building via Stochastic Approximation Algorithm: a Convergence Study
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 statistica...
متن کاملJoint Bayesian Stochastic Inversion of Well Logs and Seismic Data for Volumetric Uncertainty Analysis
Here in, an application of a new seismic inversion algorithm in one of Iran’s oilfields is described. Stochastic (geostatistical) seismic inversion, as a complementary method to deterministic inversion, is perceived as contribution combination of geostatistics and seismic inversion algorithm. This method integrates information from different data sources with different scales, as prior informat...
متن کاملStochastic Algorithm For Parameter Estimation For Dense Deformable Template Mixture Model
Estimating probabilistic deformable template models is a new approach in the fields of computer vision and probabilistic atlases in computational anatomy. A first coherent statistical framework modelling the variability as a hidden random variable has been given by Allassonnière, Amit and Trouvé in [1] in simple and mixture of deformable template models. A consistent stochastic algorithm has be...
متن کاملRandomized-direction Stochastic Approximation Algorithms Using Deterministic Sequences
We study the convergence and asymptotic normality of a generalized form of stochastic approximation algorithm with deterministic perturbation sequences. Both one-simulation and two-simulation methods are considered. Assuming a special structure of deterministic sequence, we establish sufficient condition on the noise sequence for a.s. convergence of the algorithm. Construction of such a special...
متن کاملApproximation Analysis of Stochastic Gradient Langevin Dynamics by using Fokker-Planck Equation and Ito Process
The stochastic gradient Langevin dynamics (SGLD) algorithm is appealing for large scale Bayesian learning. The SGLD algorithm seamlessly transit stochastic optimization and Bayesian posterior sampling. However, solid theories, such as convergence proof, have not been developed. We theoretically analyze the SGLD algorithm with constant stepsize in two ways. First, we show by using the Fokker-Pla...
متن کامل