EasyDeepLearn

Dirichlet distribution — where does it show up in ML?

hard

Answer

  • Dirichlet(α1,  ,  αK)\mathrm{Dirichlet}({\alpha}_{1}, \;, \;{\alpha}_{K}): distribution over probability vectors on the (K-1)-simplex (positive components summing to 1).
  • Multivariate generalization of Beta.
  • Conjugate prior for the categorical / multinomial distributions.
  • Uses: topic models (LDA — Latent Dirichlet Allocation), mixture-model weights, softmax priors, RL policy priors.
  • Concentration parameter Σαi{\Sigma}{\alpha}_{i} controls how peaked (large α) vs uniform (small α) the samples are.
Check yourself — multiple choice
  • Univariate on R
  • Prior on probability simplex; conjugate for categorical/multinomial; foundation of LDA, mixture weights, softmax priors
  • Only for regression
  • Same as Beta identically

Dirichlet: prior over prob simplex; conjugate for multinomial; used in LDA.

#distributions#bayesian

Practise Statistics Fundamentals

215 interview questions in this topic.

Related questions