CS886 - Schedule

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


Complementary Readings
Assigned Readings
Sept  14
Course overview

Sept 16
Bayesian networks, exact inference (Lecture slides)
[KF] Sect 3.1-3.2, 9.1-9.4

Sept 21
Conditional independence, approximate inference (Monte Carlo techniques (Lecture slides)
[KF] Sect 3.3, 12.1-12.3

Sept 23
Lecture canceled

Sept 28
Monte Carlo techniques continued

Sept 30
Statistical learning (Bayesian learning, maximum likelihood, maximum a posteriori hypothesis) (Lecture slides)
[KF] Sect 17.1-17.4

Oct 5
Learning from incomplete data, expectation maximization (Lecture slides)
[KF]Sect 19.1-19.2

Oct 7
Single/multi parameter models, conjugate prior
[GCSR] Chapter 2-3
Oct 12

1) Friedman, Linial, Nachman and Pe'er, Using Bayesian networks to analyze expression data, Journal of computational biology, 2000
Presenters: Catalin-Alexandru Avram, Muhammad Bilal Sheikh
2) Jaakola and Jordan, Variational probabilistic inference and the QMR-DT network, JAIR, 1999
Presenters: Anup Kumar Chalamalla, Jalaj Kumar Upadhyay
Oct 14
Single/multi parameter models, conjugate prior, exchangeability, [GCSR] Chapter 2-3
Oct 19

3) Blei, Ng and Jordan, Latent Dirichlet Allocation, JMLR, 2003
Presenters: Wenxuan Wang, Gelin Zhou
4) Fei-Fei and Perona, A Bayesian hierarchical model for learning natural scene categories, CVPR, 2005
Presenters: Clara Ines Forero Suancha, Wenye Yu
Oct 21
Informative/non-informative priors, mixture models, Bayesian clustering, Dirichlet process (aka the Chinese restaurant process) [GCSR] Chapter 5
Oct 26

5) Rasmussen, Infinite Gaussian Mixture Model, NIPS, 2000
Presenters: Jiong Xi,
6) Navarro, Griffiths, Steyvers and Lee, Modeling individual differences using Dirichlet processes, Journal of Mathematical Psychology, 2006
Presenters: Anthony Schmieder, Tommy Carpenter, Steffen Kellen
Oct 28
Hierarchical Dirichlet process (aka the Chinese restaurant franchise)
Pitman-Yor process

Project proposal due
Nov 2

7) Teh, Jordan, Beal and Blei, Hierarchical Dirichlet processes, Journal of the American Statistical Association, 2006
Presenters: Arthur Carvalho, Hu Bo
8) Wood, Archambeau, Gasthaus, James and Teh, A stochastic Memoizer for Sequence Data, ICML, 2009
Presenters: Karim Hamdan Ali, Sarah Nadi
Nov 4
Beta process (aka the Indian buffet process)

Nov 9
Lecture canceled

Nov 11

9) Ghahramani, Griffiths and Sollich, Bayesian nonparametric latent feature models, Bayesian Statistics, 2007
Presenters: Tao Wang
10) Van Gael, Teh and Ghahramani, The Infinite Factorial Hidden Markov Model, NIPS, 2009
Nov 16
Regression with Gaussian processes

Nov 18

11) Lizotte, Wang, Bowling and Schuurmans, Automatic Gait Optimization with Gaussian Process Regression, IJCAI, 2007
Presenters: Md Faizul Bari, Md Haque
12) Ko and Fox, GP-BayesFilters: Bayesian filtering using Gaussian process prediction and observation models, Autonomous Robots Journal, 2009
Presenters: Vladimir Pisanov
Nov 23
Bayesian Reinforcement Learning (Lecture Slides)

Nov 25

13) Engel, Mannor, Meir, Bayes meets Bellman: The Gaussian process approach to temporal difference learning, ICML, 2003
Presenters: Alexander Leong, Simon Benjamin Orion Parent
14) Poupart, Vlassis, Hoey and Regan, An Analytic Solution to Discrete Bayesian Reinforcement Learning, ICML, 2006
Presenters: Shehroz Khan, Dmitry Pyryeskin, Fady Samuel
Nov 30
Gaussian Process dimensionality reduction

Dec 2

15) Lawrence, Probabilistic Non-linear Principal Component Analysis with Gaussian Process Latent Variable Models, JMLR, 2005
Presenters: Ryan James Case, Chen Li, Aditya Tayal
16) Wang, Fleet, Hertzmann, Gaussian Process Dynamical Models for Human Motion, IEEE Transactions on Parttern Analysis and Machine Intelligence, 2008