J. Andrés Christen

J. Andrés Christen, Colin Fox, Diego Andrés Pérez-Ruiz et al.

Generalized Gibbs kernels are those that may take any direction not necessarily bounded to each axis along the parameters of the objective function. We study how to optimally choose such directions in a Directional, random scan, Gibbs sampler setting. The optimal direction is chosen by minimizing to the mutual information (Kullback-Leibler divergence) of two steps of the MCMC for a truncated Normal objective function. The result is generalized to be used when a Multivariate Normal (local) approximation is available for the objective function. Three Gibbs direction distributions are tested in highly skewed non-normal objective functions.

Maria L. Daza-Torres, Juan Antonio Infante del Río, Marcos A. Capistrán et al.

In this paper we demonstrate a computational method to solve the inverse scattering problem for a star-shaped, smooth, penetrable obstacle in 2D. Our method is based on classical ideas from computational geometry. First, we approximate the support of a scatterer by a point cloud. Secondly, we use the Bayesian paradigm to model the joint conditional probability distribution of the non-convex hull of the point cloud and the constant refractive index of the scatterer given near field data. Of note, we use the non-convex hull of the point cloud as spline control points to evaluate, on a finer mesh, the volume potential arising in the integral equation formulation of the direct problem. Finally, in order to sample the arising posterior distribution, we propose a probability transition kernel that commutes with affine transformations of space. Our findings indicate that our method is reliable to retrieve the support and constant refractive index of the scatterer simultaneously. Indeed, our sampling method is robust to estimate a quantity of interest such as the area of the scatterer. We conclude pointing out a series of generalizations of our method.