Skip to main content

Diagonal orthant multinomial probit models

Publication ,  Conference
Johndrow, JE; Lum, K; Dunson, DB
Published in: Journal of Machine Learning Research
January 1, 2013

Bayesian classification commonly relies on probit models, with data augmentation algorithms used for posterior computation. By imputing latent Gaussian variables, one can often trivially adapt computational approaches used in Gaussian models. However, MCMC for multinomial probit (MNP) models can be inefficient in practice due to high posterior dependence between latent variables and parameters, and to difficulties in efficiently sampling latent variables when there are more than two categories. To address these problems, we propose a new class of diagonal orthant (DO) multinomial models. The key characteristics of these models include conditional independence of the latent variables given model parameters, avoidance of arbitrary identifiability restrictions, and simple expressions for category probabilities. We show substantially improved computational efficiency and comparable predictive performance to MNP.

Duke Scholars

Published In

Journal of Machine Learning Research

EISSN

1533-7928

ISSN

1532-4435

Publication Date

January 1, 2013

Volume

31

Start / End Page

29 / 38

Related Subject Headings

  • Artificial Intelligence & Image Processing
  • 4905 Statistics
  • 4611 Machine learning
  • 17 Psychology and Cognitive Sciences
  • 08 Information and Computing Sciences
 

Citation

APA
Chicago
ICMJE
MLA
NLM
Johndrow, J. E., Lum, K., & Dunson, D. B. (2013). Diagonal orthant multinomial probit models. In Journal of Machine Learning Research (Vol. 31, pp. 29–38).
Johndrow, J. E., K. Lum, and D. B. Dunson. “Diagonal orthant multinomial probit models.” In Journal of Machine Learning Research, 31:29–38, 2013.
Johndrow JE, Lum K, Dunson DB. Diagonal orthant multinomial probit models. In: Journal of Machine Learning Research. 2013. p. 29–38.
Johndrow, J. E., et al. “Diagonal orthant multinomial probit models.” Journal of Machine Learning Research, vol. 31, 2013, pp. 29–38.
Johndrow JE, Lum K, Dunson DB. Diagonal orthant multinomial probit models. Journal of Machine Learning Research. 2013. p. 29–38.

Published In

Journal of Machine Learning Research

EISSN

1533-7928

ISSN

1532-4435

Publication Date

January 1, 2013

Volume

31

Start / End Page

29 / 38

Related Subject Headings

  • Artificial Intelligence & Image Processing
  • 4905 Statistics
  • 4611 Machine learning
  • 17 Psychology and Cognitive Sciences
  • 08 Information and Computing Sciences