Dense distributions from sparse samples: improved Gibbs sampling parameter estimators for LDA

MaRDI QIDQ5361334zbMATH OpenFDO

Authors Yannis Papanikolaou, J. R. Foulds, Timothy N. Rubin, Grigorios Tsoumakas

Publication date 27 September 2017

Full work available at URL https://arxiv.org/abs/1505.02065, http://jmlr.csail.mit.edu/papers/v18/16-526.html

zbMATH Keywords

Bayesian inferencecollapsed Gibbs samplingCVB0latent Dirichlet allocationmulti-label classificationtext miningtopic modelsunsupervised learning

Mathematics Subject Classification ID

Bayesian inference (62F15) Classification and discrimination; cluster analysis (statistical aspects) (62H30) Learning and adaptive systems in artificial intelligence (68T05) Computing methodologies for text processing; mathematical typography (68U15)

Recommendations

• Principled selection of hyperparameters in the latent Dirichlet allocation model
• 10.1162/jmlr.2003.3.4-5.993
• Online but accurate inference for latent variable models with local Gibbs sampling
• Distributed algorithms for topic models
• A spectral algorithm for latent Dirichlet allocation

Cited in

(4)

• Online multi-label dependency topic models for text classification
• Principled selection of hyperparameters in the latent Dirichlet allocation model
• Online but accurate inference for latent variable models with local Gibbs sampling
• Maximum a posteriori inference for factor graphs via Benders' decomposition

This page was built for publication: Dense distributions from sparse samples: improved Gibbs sampling parameter estimators for LDA

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5361334)