Sparse Partially Collapsed MCMC for Parallel Inference in Topic Models

DOI10.1080/10618600.2017.1366913OpenAlexW2533991995MaRDI QIDQ3391126

Mattias Villani, David Broman, Måns Magnusson, Leif Jonsson

Publication date: 28 March 2022

Published in: Journal of Computational and Graphical Statistics (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1506.03784

zbMATH Keywords

computational complexityparallel computingBayesian inferenceGibbs samplingmassive datasetslatent Dirichlet allocation

Mathematics Subject Classification ID

Statistics (62-XX)

Related Items (3)

DOLDA: a regularized supervised topic model for high-dimensional multi-class regression ⋮ Learning Topic Models: Identifiability and Finite-Sample Analysis ⋮ GPU-accelerated Gibbs sampling: a case study of the horseshoe probit model

Uses Software

• CODA
• MALLET

Cites Work

• First hitting time analysis of the independence Metropolis sampler
• Regression density estimation using smooth adaptive Gaussian mixtures
• Dirichlet and Related Distributions
• An Efficient Method for Generating Discrete Random Variables with General Distributions
• Partially Collapsed Gibbs Samplers
• The Collapsed Gibbs Sampler in Bayesian Computations with Applications to a Gene Regulation Problem
• A simple method for generating gamma variables
• 10.1162/jmlr.2003.3.4-5.993
• Gibbs Sampling Methods for Stick-Breaking Priors
• Unnamed Item
• Unnamed Item
• Unnamed Item

This page was built for publication: Sparse Partially Collapsed MCMC for Parallel Inference in Topic Models