Machine Learning Summer School 2004 - Berder Island

Advanced Statistical Learning Theory

author: Olivier Bousquet, Google

Description

This set of lectures will complement the statistical learning theory course and focus on recent advances in the domain of classification. 1- PAC Bayesian bounds: a simple derivation, comparison with Rademacher averages.
2 - Local Rademacher complexity with classification loss, Talagrand's inequality. Tsybakov noise conditions.
3 - Properties of loss functions for classification (influence on approximation and estimation, relationship with noise conditions).
4 - Applications to SVM - Estimation and approximation properties, role of eigenvalues of the Gram matrix.

Categories

Top: Computer Science: Machine Learning: Statistical Learning

You might be experiencing some problems with Your Video player.

*Slides*
0:01	Statistical Learning Theory
0:35	Roadmap (1)
2:21	Roadmap (2)
2:49	Lecture 1
3:28	Learning and Inference
4:51	Pattern recognition
6:09	Approximation/Interpolation
8:48	Occam’s Razor
10:52	No Free Lunch
13:34	Assumptions
14:28	Goals
15:39	Probabilistic Model
17:56	Probabilistic Model
19:43	Probabilistic Model
23:26	Target function
29:34	Assumptions about P
32:41	Approximation/Interpolation (again)
33:10	Overfitting/Underfitting
34:03	Empirical Risk Minimization
35:25	Approximation/Estimation
38:13	Structural Risk Minimization
40:15	Regularization
41:41	Bounds (1)
42:42	Bounds (2)

Lecture rating

People found this lecture:
Worth seeing
because it is:
Valuable and informative
Well presented
Easily understandable
Acceptably recorded
You need to login to cast your vote.

Report a problem or upload files

If you have found a problem with this lecture or would like to send us extra material, articles, exercises, etc., please use our ticket system to describe your request and upload the data.
Enter your e-mail into the 'Cc' field, and we will keep you updated with your request's status.