Approximate Bayesian Inference for Latent Gaussian Models

By Sara Martino. 2007

314 citations recorded by the source corpus.

View Paper: https://www.semanticscholar.org/paper/eea42c2758ea89ac98713d66743d50ad74736475

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Citations in the corpus

On the relationship between conditional (CAR) and simultaneous (SAR) autoregressive models (2017, methodology): “CAR models form the basis for Gaussian Markov random fields (Rue and Held, 2005) and the popular integrated nested Laplace approximation methods (INLA, Rue et al., 2009), and SAR models are popular in geographic information systems (GIS) with the GeoDa software (Anselin et al., 2006).”
Approximate Bayesian inference for latent Gaussian models by using integrated nested Laplace approximations (2009, unknown): “In this paper, we solve all the remaining issues in Rue and Martino (2007), and present a fully automatic approach for approximate inference in latent Gaussian models which we name integrated nested Laplace approximations (INLAs).”
Data Integration for Large-Scale Models of Species Distributions. (2020, methodology): “These approximations have been combined with efficient methods for approximating the continuous space in the INLA software [67,68], which makes it possible to fit many complex ecological models efficiently using point”
Generalized Gaussian Process Regression Model for Non-Gaussian Functional Data (2014, methodology): “However, as pointed out in Section 4.1 in Rue, Martino, and Chopin (2009), the error rate of the approximation (14) may be O(1) since the dimension of τm increases with the sample size Nm.”
Twenty years of P-splines (2015, methodology): “It is also possible to use the R-INLA (Rue et al., 2009) package for fitting additive models with P-splines.”
On Variational Bayes Estimation and Variational Information Criteria for Linear Regression Models (2014, methodology): “In contexts where decisions need to be made quickly Markov Chain Monte Carlo (MCMC) methods for the analysis of Bayesian models can be deemed to be too slow in practice (Rue, Martino & Chopin 2009; Volant, Magniette & Robin 2012).”
Variational inference in nonconjugate models (2012, methodology): “Rue et al. (2009) used them for inference in latent Gaussian models.”
Bayesian hierarchical modeling of extreme hourly precipitation in Norway (2013, background): “However, the current parameterization is common in Bayesian contexts, for instance in the R-INLA toolbox (http://www.r-inla.org, Rue et al., 2009), and is chosen since derivations related to posterior densities are considerably easier in this representation.”
Bayesian Workflow (2020, methodology): “When coupled with HMC, this marginalization scheme can, depending on the cases, be more effective than reparameterization, if sometimes at the cost of a bias; for a discussion on the topic, see Margossian et al. (2020a).”
Bayesian forecasting in economics and finance: A modern review (2022, methodology): “…Sisson and Fan, 2011; Sisson et al., 2019), Bayesian synthetic likelihood (BSL) (Price et al., 2018), variational Bayes (VB) (Blei et al., 2017), and integrated nested Laplace approximation (INLA) (Rue et al., 2009), and produce what are termed ‘approximate’ forecast, or predictive distributions.”