Back to Search
Start Over
Empirical study on variational inference methods for topic models.
- Source :
-
Journal of Experimental & Theoretical Artificial Intelligence . Feb2018, Vol. 30 Issue 1, p129-142. 14p. - Publication Year :
- 2018
-
Abstract
- In topic modelling, the main computational problem is to approximate the posterior distribution given an observed collection. Commonly, we must resort to variational methods for approximations; however, we do not know which variational variant is the best choice under certain settings. In this paper, we focus on four topic modelling inference methods, including mean-field variation Bayesian, collapsed variational Bayesian, hybrid variational-Gibbs and expectation propagation, and aim to systematically compare them. We analyse them from two perspectives, i.e. the approximate posterior distribution and the type of-divergence; and then empirically compare them on various data-sets by two popular metrics. The empirical results are almost matching our analysis, where they indicate that CVB0 may be the best variational variant for topic models. [ABSTRACT FROM PUBLISHER]
Details
- Language :
- English
- ISSN :
- 0952813X
- Volume :
- 30
- Issue :
- 1
- Database :
- Academic Search Index
- Journal :
- Journal of Experimental & Theoretical Artificial Intelligence
- Publication Type :
- Academic Journal
- Accession number :
- 127071531
- Full Text :
- https://doi.org/10.1080/0952813X.2017.1409277