A note on variational Bayesian factor analysis

Jian-hua ZHAO, Leung Ho Philip YU

Research output: Contribution to journalArticlespeer-review

15 Citations (Scopus)

Abstract

Existing works on variational bayesian (VB) treatment for factor analysis (FA) model such as [Ghahramani, Z., & Beal, M. (2000). Variational inference for Bayesian mixture of factor analysers. In Advances in neural information proceeding systems. Cambridge, MA: MIT Press; Nielsen, F. B. (2004). Variational approach to factor analysis and related models. Master's thesis, The Institute of Informatics and Mathematical Modelling, Technical University of Denmark.] are found theoretically and empirically to suffer two problems: ① penalize the model more heavily than BIC and ② perform unsatisfactorily in low noise cases as redundant factors can not be effectively suppressed. A novel VB treatment is proposed in this paper to resolve the two problems and a simulation study is conducted to testify its improved performance over existing treatments. Copyright © 2008 Elsevier Ltd. All rights reserved.
Original languageEnglish
Pages (from-to)988-997
JournalNeural Networks
Volume22
Issue number7
Early online dateNov 2008
DOIs
Publication statusPublished - Sep 2009

Citation

Zhao, J.-H., & Yu, P. L. H. (2009). A note on variational Bayesian factor analysis. Neural Networks, 22(7), 988-997. doi: 10.1016/j.neunet.2008.11.002

Keywords

  • Factor analysis
  • VB
  • BIC

Fingerprint

Dive into the research topics of 'A note on variational Bayesian factor analysis'. Together they form a unique fingerprint.