CS886 Winter09 - Schedule

This is a tentative schedule only.  As the course progresses, the schedule will be adjusted.

References:
Lecture
 Topics
 Complementary Readings
 Assigned Readings
Jan 7
 Course overview

Jan 12
 basics of probabilities and statistics
 [RN Chapt 13]
[GCSR Chapt 1]
Jan 14
 Bayesian networks, exact inference
lecture slides
 [RN Chapt 14]
Jan 19
 lecture canceled

Jan 21
 lecture canceled

Jan 26
 Approximate inference (Monte Carlo techniques) [GCSR Chapt 11]
[RN Sect 14.5]
David MacKay, 1998, An introduction to Monte Carlo Methods
Jan 28
 Statistical learning (Bayesian learning, maximum likelihood, maximum a posteriori hypothesis)
lecture slides
 [RN Sect 20.1-3]
Feb 2
 Single parameter models, conjugate priors
 [GCSR Chapt 2]
 David Heckerman, A Tutorial on Learning with Bayesian Networks
Presenters: Sergey Savinov, Sevag G. Gharibian, Tuong (Teresa) Luu
Feb 4
 Informative/non-informative priors
 [GCSR Chapt 2]
Feb 9
 Multi-parameter models
 [GCSR Chapt 3]
 Bernardinelli, Clayton and Montomoli (1995) Bayesian estimates of disease maps: how important are priors? Statistics in Medicine 14, 2411--2431 (not available online, get it from the library)
Presenters: Denis Ho Bun Yuen, Bo Wang and Ruitong Huang
Feb 11
 Hierarchical models
 [GCSR Chapt 5]
Feb 16
 reading break

Feb 18
 reading break

Feb 23
 Exponential class, MCMC (Metropolis-Hastings)
Piotr Gmytrasiewicz and Prashant Doshi, "A Framework for Sequential Planning in Multiagent Settings", in Journal of AI Research (JAIR), Vol 24: 49-79, 2005
Presenters: John Champaign, Thomas Reidemeister, Igor Pavlovitch Kiselev and Lachlan Thomas Dufton
Feb 25
 Exchangeability, mixture models, Bayesian clustering
Project proposal due
Mar 2
 Dirichlet process (aka the Chinese restaurant process) Ranganathan, 2004, The Dirichlet Process Mixture (DPM) Model
 DM Blei, AY Ng, MI Jordan, Latent Dirichlet Allocation, Journal of Machine Learning Research, 2003.
Presenters: Ahmad Alyoubi, Ting Liu
Mar 4
 Hierarchical Dirichlet process (aka the Chinese restaurant franchise)
 Michael Jordan's talk on Dirichlets Processes
Mar 9
 Pitman-Yor process
YW Teh, MI Jordan, MJ Beal, DM Blei, Hierarchical Dirichlet Processes
Presenters: Jakub Michal Truszkowski, Hussein Abdul Hirjee, Krzysztof Borowski and Babak Alipanahi Ramandi
Mar 11
 Beta process (aka the Indian buffet process)

Mar 16
 Gaussian process
 [RW Chapt 1]
 Hierarchical Bayesian nonparametric models with applications. Y. W. Teh and M. I. Jordan. In N. Hjort, C. Holmes, P. Mueller, and S. Walker (Eds.), Bayesian Nonparametrics in Practice, Cambridge, UK: Cambridge University Press, to appear.
Presenters: Mohammad Yousef Akhavein Sohrabi, Mazen Melibari, Jeff Pound
Mar 18
 Regression with Gaussian processes
 [RW Chapt 2]
Mar 23
 Classification with Gaussian processes
 [RW Chapt 3]
 Y. Engel, P. Szabo, and D. Volkinshtein. Learning to control an octopus arm with Gaussian process temporal difference methods. In Yair Weiss, Bernhard Schölkopf, and John C. Platt, editors, Advances in Neural Information Processing Systems 18, pages 347-354, Cambridge, MA, U.S.A., 2006. The MIT Press.
Presenters: Stephane Bonardi, Hiren Patel and Kush Patel
Mar 25
 Classification with Gaussian processes
 [RW Chapt 3]
Mar 30
 Covariance functions for Gaussian processes
 [RW Chapt 4]
 A. Kapoor, K. Grauman, R. Urtasun, and T. Darell. Active learning with Gaussian processes for object categorization. In Proceedings of the International Conference in Cmputer Vision, 2007.
Presenters: Prashant Gaharwar and Yichuan Tang
Apr 1
 Model selection for Gaussian processes [RW Chapt 5]
Apr 6
 Relation between Gaussian processes and other models (e.g., support vector machines)
 [RW Chapt 6]
 P. Sollich. Bayesian methods for support vector machines: Evidence and predictive class probabilities. Machine Learning, 46(1-3):21-52, 2002.
Presenters: Ying Liu and Francisco Claude
Apr 8
 Relation between Gaussian processes and other models (e.g., support vector machines) [RW Chapt 6]