Parallelized integrated nested Laplace approximations for fast Bayesian inference
From MaRDI portal
Publication:2677902
DOI10.1007/S11222-022-10192-1zbMATH Open1502.62016arXiv2204.04678OpenAlexW4312118372MaRDI QIDQ2677902FDOQ2677902
Authors: Lisa Gaedke-Merzhäuser, Olaf Schenk, Håvard Rue, Janet van Niekerk 
Publication date: 9 January 2023
Published in: Statistics and Computing (Search for Journal in Brave)
Abstract: There is a growing demand for performing larger-scale Bayesian inference tasks, arising from greater data availability and higher-dimensional model parameter spaces. In this work we present parallelization strategies for the methodology of integrated nested Laplace approximations (INLA), a popular framework for performing approximate Bayesian inference on the class of Latent Gaussian models. Our approach makes use of nested OpenMP parallelism, a parallel line search procedure using robust regression in INLA's optimization phase and the state-of-the-art sparse linear solver PARDISO. We leverage mutually independent function evaluations in the algorithm as well as advanced sparse linear algebra techniques. This way we can flexibly utilize the power of today's multi-core architectures. We demonstrate the performance of our new parallelization scheme on a number of different real-world applications. The introduction of parallelism leads to speedups of a factor 10 and more for all larger models. Our work is already integrated in the current version of the open-source R-INLA package, making its improved performance conveniently available to all users.
Full work available at URL: https://arxiv.org/abs/2204.04678
Recommendations
- Parallel algorithms for Bayesian inference in spatial Gaussian models
- Bayesian computing with INLA: new features
- Approximate Bayesian inference for latent Gaussian models by using integrated nested Laplace approximations (with discussion)
- Bayesian inference with INLA
- Markov chain Monte Carlo with the integrated nested Laplace approximation
Cites Work
- Gaussian Markov Random Fields
- Bayesian computing with INLA: new features
- Direct Methods for Sparse Linear Systems
- Approximate Bayesian inference for hierarchical Gaussian Markov random field models
- Approximate Bayesian inference for latent Gaussian models by using integrated nested Laplace approximations (with discussion)
- A Fast and High Quality Multilevel Scheme for Partitioning Irregular Graphs
- Modeling Spatial Variation in Leukemia Survival Data
- Title not available (Why is that?)
- An explicit link between Gaussian fields and Gaussian Markov random fields: the stochastic partial differential equation approach
- The Evolution of the Minimum Degree Ordering Algorithm
- Title not available (Why is that?)
- Nested Dissection of a Regular Finite Element Mesh
- Robust diagnostic regression analysis
- Title not available (Why is that?)
- Title not available (Why is that?)
- Title not available (Why is that?)
- Computing the Minimum Fill-In is NP-Complete
- A first course in numerical methods
- Applied Bayesian Modelling
- Parallel Algorithms for Sparse Linear Systems
- Computing entries of the inverse of a sparse matrix using the FIND algorithm
- Title not available (Why is that?)
- Latent Gaussian modeling and INLA: a review with focus on space-time applications
- State-of-the-art sparse direct solvers
- Smart gradient - an adaptive technique for improving gradient estimation
- A Bayesian general linear modeling approach to cortical surface fMRI data analysis
Cited In (15)
- A TMB approach to study spatial variation in weather-generated claims in insurance
- A flexible Bayesian tool for CoDa mixed models: logistic-normal distribution with Dirichlet covariance
- Integrated nested Laplace approximations for large-scale spatiotemporal Bayesian modeling
- Fast Bayesian inference of block nearest neighbor Gaussian models for large data
- Massive parallelization of serial inference algorithms for a complex generalized linear model
- A fast lattice algorithm for PARCOR parameter estimation based on an approximate likelihood
- Bayesian survival analysis with INLA
- Accelerated parallel non-conjugate sampling for Bayesian non-parametric models
- A new avenue for Bayesian inference with INLA
- Temporal Parallelization of Bayesian Smoothers
- Bayesian computing with INLA: new features
- Past, present and future of software for Bayesian inference
- Efficient posterior integration in stable paretian models
- Fast automatic Bayesian cubature using lattice sampling
- Parallel algorithms for Bayesian inference in spatial Gaussian models
Uses Software
This page was built for publication: Parallelized integrated nested Laplace approximations for fast Bayesian inference
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2677902)
