Machine Learning II & Machine Learning Journal Club (2009/2010)

Bayesian Nonparametrics

18/01, 19/01: Yee Whye presents an introduction to Bayesian nonparametrics.

• MLSS 2009 version on videolectures.
• Introduction to Dirichlet Processes.
• Review of Hierarchical Bayesian Nonparametric Models.

25/01, 26/01: Vinayak, Dilan present MCMC Inference for Dirichlet Process Mixtures.

• Neal: Markov Chain Sampilng Methods for Dirichlet Process Mixture Models.
• Jain Neal: A Split-merge Markov Chain Monte Carlo procedure for the Dirichlet Process Mixture Model.
• Additional reading:
  • Jain Neal: Splitting and Merging Components of a Nonconjugate Dirichlet Process Mixture Model.

19/01: Vinayak, Dilan present the basic papers on Dirichlet Processes.

• Ferguson: A Bayesian Analysis of Some Nonparametric Problems.

01/02: Dilan presents:

• Blackwell MacQueen: Ferguson Distributions via Polya Urn Schemes.

01/02: Dilan, Charles present:

• Kingman book chapter on Completely Random Measures. Photocopies available upon request
• Additional reading:
  • Kingman: Completely Random Measure.

02/02: Dilan, Jan present:

• Kim: Nonparametric Bayesian Estimators for Counting Processes.
• Additional readings:
  • Griffiths Ghahramani: Infinite Latent Feature Models and the Indian Buffet Process.
  • Hjort: Nonparametric Bayesian Estimators based on Beta Processes in Models for Life History Data.
  • Thibaux Jordan: Hierarchical Beta Processes and the Indian Buffet Process.
  • Kim Lee: On Posterior Consistency of Survival Models.