Modelling in Classification and Statistical Learning Workshop 2004 - Eindhoven

Penalized empirical risk minimization in the estimation of thresholds

author:Leila Mohammadi, Eurandom
published: Feb. 25, 2007, recorded: October 2004, views: 53

You might be experiencing some problems with Your Video player.

Slides

Slides
0:01	Penalized empirical risk minimization in the estimation of thresholds
0:25	Introduction
2:10	Empirical risk
3:21	Penalized empirical risk minimizer
6:06	Penalized empirical risk minimizer
8:25	Lemma 1.
15:10	Assumption (A).
20:37	Sketch of a proof
22:38	Sketch of a proof
23:40	Sketch of a proof
25:00	Assumption (A).
25:20	Sketch of a proof
25:50	Assumption (A).
25:54	Sketch of a proof
26:15	Assumption (A).
26:23	Theorem 2.
27:09	An application:
30:50	An application:
31:03	Assumption (B).
36:40	Lemma 2.

Related content

Visitors who watched this lecture also watched...

13:36

Query Suggestions for Mobile Search: Understanding Usage Patterns
111 views - Maryam Kamvar, 2008

15:41

Debate
199 views - Lise Getoor, Pedro Domingos, Thomas Dietterich, Bernhard Pfahringer, Prasad Tadepalli, 2007

01:07:10

Stability for selecting the number of clusters: literature review, questions, and ideas
406 views - Ulrike von Luxburg, 2007

04:22:56

Gaussian Processes
1343 views - Carl Edward Rasmussen, 2003

57:46

Invited Talk: Empirical Risk Minimization with Statistics of Higher Order with Examples from Bipartite Ranking
42 views - Nicolas Vayatis, 2009

01:07:01

Cluster Stability for Finite Samples
105 views - Ohad Shamir, 2007

59:51

A formal analysis of stability - lessons and open questions
146 views - Shai Ben-David, 2007

24:03

Safety/Risk Assessment of GMOs, using GM Crops as an Example
77 views - Wendy Craig, 2008

15:44

Integrated Risk Reduction of Information-based Infrastructure Systems
28 views - Hermann Dellwing, 2007

02:15:42

Reinforcement Learning Theory
910 views - John Langford, 2006

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.

Lecture popularity: You need to login to cast your vote.