CS 281B / Stat 241B, Spring 2006:
Statistical Learning Theory
Presentation Topics
Please sign up for a date and topic by emailing Ambuj.
Presentations will be in groups of 2, and for a total of 25 minutes.
[*] indicates we do not need any more volunteers to present the paper.
Pattern Classification
Kernel Methods, Support Vector Machines
Ensemble Methods
Universal prediction
- Tuesday, March 21.
[*]
`How to use expert advice.'
N. Cesa-Bianchi, Y. Freund, D.P. Helmbold, D. Haussler, R. Schapire,
and M.K. Warmuth.
- Thursday, March 23.
`On the generalization ability of on-line learning algorithms.'
N. Cesa-Bianchi, A. Conconi, and C. Gentile.
- Tuesday, April 4.
[*]
` Worst-Case Bounds for Gaussian Process Models'
S. M. Kakade, M. W. Seeger, and D. P. Foster.
- Thursday, April 6.
[*]
`On prediction of individual sequences'
N. Cesa-Bianchi and G. Lugosi
Risk Bounds
- Tuesday, April 11.
`Process consistency for AdaBoost.'
W. Jiang.
- Thursday, April 13.
[*]
`Predicting {0, 1}-Functions on Randomly Drawn Points'
D. Haussler, N. Littlestone and M. K. Warmuth.
- Tuesday, April 18.
[*]
`PAC generalization bounds for co-training.'
S. Dasgupta, M.L. Littman, and D. McAllester.
- Thursday, April 20.
[*]
`The sample complexity of learning fixed-structure
Bayesian nets.'
S. Dasgupta.
- Thursday, April 25.
[*]
`On the rate of convergence of regularized boosting methods.'
G. Blanchard, G. Lugosi and N. Vayatis.
- Thursday, April 27.
`Fast Rates for Support Vector Machines using Gaussian Kernels.'
I. Steinwart and C. Scovel.
- Tuesday, May 2.
[*]
`Consistency and convergence rates of one-class SVM and related
algorithms.' (See Section 3.)
R. Vert and J.-P. Vert.
Back to course home page