A1292
Title: Integration methods in approximate Bayesian inference
Authors: Yanbo Tang - Imperial College London (United Kingdom) [presenting]
Abstract: The application of integration methods is examined for approximating key quantities associated with complex posterior distributions and marginal likelihoods, along with their corresponding statistical guarantees. Particular attention is given to two classes of integration techniques: quadrature methods and grid-based Monte Carlo methods. Their computational complexities are analyzed in the context of high-dimensional settings. Finally, illustrative examples demonstrating the practical implementation of these methods are presented.
