FAST--A Fast And Scalable Topic-Modeling Toolbox

Submitted by on Aug 25 2015 } Suggest Revision
By: Arthur Asuncion and colleagues
Resource Type:
Code
License:
Language:
Matlab, C
Data Format:

Description

This toolbox includes parallel/distributed algorithms, statistical acceleration techniques, and efficient inference methods for more specialized models: Distributed collapsed Gibbs sampling for LDA, Asynchronous distributed collapsed Gibbs sampling for LDA, Fast collapsed Gibbs sampling for LDA, Fast collapsed variational inference (CVB0) for LDA, Efficient collapsed Gibbs sampling for the Relational Topic Model. This collection of software focuses on efficient and scalable inference algorithms for topic models.
Post comment
Cancel