| CompSci 295 METHDS-GRAPH MODELS | ||||||||||||||||
| Code | Typ | Sec | Unt | Instructor | Time | Place | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 35730 | Lec | H | 4 | IHLER, A. | TuTh 12:30- 1:50p | ICS 259 | ||||||||||
This course is a highly participatory exploration of recent research directions in learning and inference algorithms for probabilistic models, particularly graphical models (Bayes' nets, Markov random fields, et cetera). The class is structured to include both a student-led seminar portion, similar to a reading group but with more week-to-week structure, and a lecture part in which we will cover additional background, extensions and other related material. The course provides the opportunity to read and understand recent work relevant to research in graphical models and machine learning, while giving the course more structure and continuity than a typical seminar or reading group.
Background. Although the first week or two will provide a brief introduction to graphical models, students are expected to have some basic background, such as one of CS 271, 274-276 or equivalent. If unsure, send me an email or come by my office (BH4066) to discuss your background.
Course format. You, the student, will have the ability to influence the exact topics we cover. At the first meeting, we will decide on the set and sequence of topics, and students will divide into small groups, each of which will choose one topic for their own. Each week, one group will be responsible for reviewing the literature associated with their topic (with assistance from myself), providing a short written summary beforehand for the rest of the class, and leading a presentation and discussion of the papers during Tuesday class. The Thursday lecture will then proceed to elaborate in more depth, covering extensions or other closely related topics, or giving more background and details, depending on the subject. It is possible (even likely) that we will not make it through all the topics; priority will be given to "Tuesday" topics, with additional coverage by myself during the lecture portion on Thursday if necessary.
Note: although there are one or more papers associated with each day's lecture, they should be considered (non-required) supplemental reading -- primary reading and preparation for the week come from the student-prepared summaries for Tuesday.
Topics.
A selection of possible topics follows; these are subject to change and re-arrangment
in the future. If you have additional ideas or suggestions for topics you'd like to see
covered, let me know by email or in person and we will discuss them on the first day.
Week 1 | 01/08/2008 |
Alex |
Initial meeting and organization; introduction to graphical models |
|
|
||
| 01/10/2008 |
Alex |
introduction continued; exponential families, discrete and Gaussian distributions; inference in trees |
|
|||
Week 2 | 01/15/2008 |
Alex |
Examples of graphical models; exact vs MCMC vs variational methods |
|
Wainwright and Jordan 2003 [PDF] |
||
| 01/17/2008 |
Alex |
Variational methods I: functionals, convexity; duality of parameters and marginals; the marginal polytope |
|
|||
Week 3 | 01/22/2008 |
TBD |
Variational methods II: mean field, belief propagation |
|
|||
| 01/24/2008 |
Alex |
Variational methods III: belief propagation and tree-reweighted BP |
|
Wainwright et al. 2003 [PDF] |
||
Week 4 | 01/29/2008 |
Drew |
"Efficient" methods for belief propagation |
[ Summary ] |
|||
| 01/31/2008 |
Alex |
Belief propagation and mixing properties |
|
Tatikonda and Jordan 2001 [PDF] |
||
Week 5 | 02/05/2008 |
TBD |
Introduction to Markov chain Monte Carlo methods |
|
TBD |
||
| 02/07/2008 |
Dave Newman |
Introduction to graphical models for topic modeling and text data |
[ Slides ] |
TBD |
||
Week 6 | 02/12/2008 |
Todd |
Dirichlet processes and applications to topic modeling |
[ Summary ] |
|||
| 02/14/2008 |
Alex |
More on Dirichlet Processes; Stick-breaking representations |
|
|||
Week 7 | 02/19/2008 |
Ian |
Hierarchical Dirichlet processes and other "infinite state" models |
[Slides ] |
|||
| 02/21/2008 |
Alex |
OPEN |
[ Summary ] [ Slides ] |
TBD |
||
Week 8 | 02/26/2008 |
Ken |
Learning model structure via penalized regression |
[ Slides ] |
Wainwright et al . 2006 [PDF] |
||
| 02/28/2008 |
Ajay |
Learning mixtures of trees |
[ Summary ] [ Slides ] |
|||
Week 9 | 03/04/2008 |
Dave |
Max product and linear programming connections |
[ Summary ] |
|||
| 03/06/2008 |
Alex |
OPEN |
[ Summary ] [ Slides ] |
TBD |
||
Week 10 | 03/11/2008 |
Chaitanya C. |
Variational approaches to LDA and topic modeling |
Blei and Jordan 2004 [PDF] |
|||
| 03/13/2008 |
Alex |
OPEN |
[ Summary ] [ Slides ] |
TBD |
||