Algorithms of the LDA model [REPORT]

2013/07/01 by Jaka Ṡ́peh, Špeh, Jaka, Andrej Muhič +3 · 1 citation
Computer Science · Mathematics · #Bayesian Methods and Mixture Models #FOS: Computer and information sciences #Gaussian Processes and Bayesian Inference #Information Retrieval (cs.IR) #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Statistical Methods and Inference

paper · pdf · doi:10.48550/arxiv.1307.0317

openalex publication_date 2013/07/01 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

We review three algorithms for Latent Dirichlet Allocation (LDA). Two of them are variational inference algorithms: Variational Bayesian inference and Online Variational Bayesian inference and one is Markov Chain Monte Carlo (MCMC) algorithm -- Collapsed Gibbs sampling. We compare their time complexity and performance. We find that online variational Bayesian inference is the fastest algorithm and still returns reasonably good results.

Cited by

• Semi-Automatic Terminology Ontology Learning Based on Topic Modeling

Related

• Dense Distributions from Sparse Samples: Improved Gibbs Sampling Parameter Estimators for LDA
• Incremental Variational Inference for Latent Dirichlet Allocation
• Rethinking Collapsed Variational Bayes Inference for LDA
• Blocking Collapsed Gibbs Sampler for Latent Dirichlet Allocation Models
• Guaranteed Model Order Estimation and Sample Complexity Bounds for LDA