MLRG/spring09
From ResearchWiki
(Difference between revisions)
m (→Participants) |
m (→Schedule and Readings) |
||
| Line 46: | Line 46: | ||
| R 12 Feb | | R 12 Feb | ||
|| ''Rademacher complexity''; [http://jmlr.csail.mit.edu/papers/v3/bartlett02a.html Bartlett and Mendelson] | || ''Rademacher complexity''; [http://jmlr.csail.mit.edu/papers/v3/bartlett02a.html Bartlett and Mendelson] | ||
| - | || | + | || Piyush |
|- | |- | ||
| R 19 Feb | | R 19 Feb | ||
Revision as of 19:15, 5 January 2009
Contents |
CS7941: Theoretical Machine Learning
Time: Thr 10:45-12:05pm (see schedule for each week)
Location: MEB 3105
Expected Student Involvement
TBD.
Participants
- Hal Daumé III, Assistant Professor, School of Computing
- Arvind Agarwal, PhD Student, School of Computing
- Nathan Gilbert, PhD Student, School of Computing
- Piyush Rai, PhD Student, School of Computing
Schedule and Readings
| Date | Papers | Presenters |
|---|---|---|
| Introduction to Computational Learning Theory | ||
| R 15 Jan | PAC Learning; Kearns and Vazirani, Chapter 1 | Hal |
| R 22 Jan | Occam's Razor; Kearns and Vazirani, Chapter 2 | |
| R 29 Jan | Learning with Noise; Kearns and Vazirani, Chapter 5 | |
| Sample Complexity and Infinite Hypothesis Spaces | ||
| R 5 Feb | VC dimension; Kearns and Vazirani, Chapter 3 | Arvind |
| R 12 Feb | Rademacher complexity; Bartlett and Mendelson | Piyush |
| R 19 Feb | Covering numbers; Zhang | |
| R 26 Feb | Pseudodimension, Fat Shattering Dimension; Bartlett, Long and Williamson | |
| R 5 Mar | PAC-Bayes; McAllester | Ruihong |
| Boosting | ||
| R 12 Mar | Introduction to Boosting; Kearns and Vazirani, Chapter 4 | Arvind |
| R 26 Mar | Boosting and margins; Schapire, Freund, Bartlett and Lee | |
| Assorted Topics | ||
| R 2 Apr | Hardness of learning; Kearns and Vazirani, Chapter 6 | |
| R 9 Apr | Portfolio selection; Blum and Kalai | |
| R 16 Apr | Game theory and learning; Freund and Schapire | Nathan |
| R 23 Apr | TBD | |
Related Classes
- Machine Learning Theory, CMU by Avrim Blum
- Computational Learning Theory, Penn by Michael Kearns and Koby Crammer
- Learning Theory, TTI-C by Sham Kakade
- Introduction to Computational Learning Theory, Columbia by Rocco Servedio
- Theoretical Machine Learning, Princeton by Rob Shapire
- The Computational Complexity of Machine Learning, U Texas by Adam Klivans
