Schedule
*** - Presented in seminar; Assigned as required reading
** - Material alluded to in seminar; highly useful reading
* - Very interesting and/or specialized reading
| Meeting Week | Date | Topic | Presenters | Material |
|---|---|---|---|---|
| 1 | W Jan 19 4:30-6 | scheduling mtg | ||
| 2 | M Jan 24 4-6 | Game Theory | Cathy Ruby / Mike Dinolfo | A Short, Introductory Report on Game Theory - *** [pdf] Non Zero Sum and Nash Equilibrium slides by Andrew Moore - *** [pdf] An Introductory Sketch of Game Theory - *** [html] Computation Game Theory Slides, taught by Michael Kearns - *** [pdf] Interactive Tutorials in Game Theory - ** [htm] Graphical Models for Game Theory - ** [pdf] A Bibliography of Cooperative Games: Value Theory - * [html] |
| W Jan 26 4-6 | ||||
| 3 | M Jan 31 4-6 | Monte Carlo | Matt Beal | Introduction to MCMC using chapter 29 of MacKay's book |
| W Feb 02 4-6 | Praveen Krishnamurthy* | importance sampling, rejection sampling chapter 29 of MacKay's book |
||
| 4 | M Feb 07 4-6 | Karthik Sridharan | Metropolis-Hastings and Gibbs sampling chapter 29 of MacKay's book theory of Markov chains section 3.3 of Neal's technical report Neal, R. M. (1993) Probabilistic Inference Using Markov Chain Monte Carlo Methods, Technical Report CRG-TR-93-1, Dept. of Computer Science, University of Toronto, 144 pages |
|
| W Feb 09 4-6 | Praveer Mansukhani | slice sampling, Gibbs sampling, exact sampling chapter 29 of MacKay's book |
||
| 5 | W Feb 16 2:50-6 | Sankalp Nayak | Hamiltonian Monte Carlo: section 5,0 of Neal's technical report chapter 30 of MacKay's book exact sampling: chapter 32 of Mackay's book O'Hagan: Monte Carlo is fundamentally unsound [pdf] |
|
| 6 | W Feb 23 2:50-6 | Inference on Graphs | Chetan Bhole | conditional independence relationships, review of Bayesian networks chapter 16 of Mackay's book chapter 1 of Learning in Graphical Models [pdf] |
| 7 | W Mar 02 2:50-6 | Kiran Garaga Lokeswarappa |
a little of 1st ch of LIGrModels, intro to BNs, Weiss & Jordan paper, ch 26 mackay (factor graphs)
1st chapter on Learning in Graphical models "Introduction to Inference for Bayesian Networks", Robert Cowell.
Murphy reference
Weiss & Jordan paper "Graphical Models: Probabilistic Inference", Jordan & Weiss.
Following is a list of materials I found useful. First one quotes
Michael Jordan in first two paragraphs which I felt is a very good
description of Graphical Models.
1) http://www.cs.ubc.ca/~murphyk/Bayes/bayes.html
2) http://www.stanford.edu/~paskin/gm-short-course/lec3.pdf
3) http://www.cs.wisc.edu/~dpage/cs731/lecture5.ppt#256,1,Junction
Trees: Motivation
Also CSE 574 slides on graphcial models and time series analysis/.
|
|
| 8 | W Mar 09 2:50-6 | Variational methods | Karthi Bandi | variational methods basics, convex duality, QMR-DT An Introduction to Variational Methods for Graphical Models [ps.gz] |
| 9 | W Mar 16 2:50-6 | spring break | ||
| 10 | W Mar 23 2:50-6 | Yu Wang | block and sequential methods, approximate EM An Introduction to Variational Methods for Graphical Models [ps.gz] |
|
| 11 | W Mar 30 2:50-6 | Kernel methods / SVMs | Jiang Li | Review of kernel methods, support vector machines, kernel Fisher discriminants, kernel PCA K.-R. Mueller, S. Mika, G. Ratsch, K. Tsuda, and B. Schoelkopf. An introduction to kernel-based learning algorithms. [pdf] IEEE Neural Networks, 12(2):181-201, May 2001. |
| 12 | W Apr 06 2:50-6 | cancelled | ||
| 13 | W Apr 13 2:50-6 | Neil Fernandes | Bounds on generalization error O. Bousquet, S. Boucheron, and G. Lugosi Introduction to Statistical Learning Theory. [pdf] G. Lugosi Concentration-of-measure inequalities. [pdf] |
|
| 14 | W Apr 20 2:50-6 | PAC Bayes | Matt Beal | The RKHS idea |
| 15 | W Apr 27 2:50-6 | - | - | - |