Sign inSign up
Algorithms for Lipschitz Learning on Graphs thumbnail
slide-image
Pause
Mute
Subtitles not available
Playback speed
0.25
0.5
0.75
1
1.25
1.5
1.75
2
Full screen

Algorithms for Lipschitz Learning on Graphs

Published on Aug 20, 20152943 Views

Sushant Sachdeva

We develop fast algorithms for solving regression problems on graphs where one is given the value of a function at some vertices, and must find its smoothest possible extension to all vertices. The ex

COLT 2015 - Paris

Related categories

Active LearningComputational Learning TheoryOn-line LearningReinforcement LearningSemi-supervised Learning

Chapter list

Algorithms for Lipschitz Learning on Graphs00:00
Learning on Graphs - 100:09
Learning on Graphs - 200:46
The Basics01:14
Preliminaries - 101:18
Preliminaries - 201:26
Preliminaries - 301:32
Preliminaries - 401:33
Preliminaries - 501:58
Two Smooth Extensions - 102:54
Two Smooth Extensions - 203:28
Two Smooth Extensions - 304:00
Two Smooth Extensions - 404:39
Two Smooth Extensions - 504:50
Two Smooth Extensions - 604:54
Other Smooth Extensions05:02
Concern with 2-Minimizer05:43
2-Minimizer vs Lex06:22
Other Smooth Extensions07:09
Algorithms07:35
Some Definitions07:44
Steepest Terminal PAir09:04
Finding a Steepest Pair09:59
Simple Case: Star Graph10:33
Directed Graphs11:26
Stability and Regularization12:18
Noise Stability12:21
l1 Regularization 12:49
l0 Regularization 13:36
Experiments14:24
Fast Implementations14:34
Detecting Spam Webpages - 115:09
Detecting Spam Webpages - 216:30
Comparison16:48
Conclusion17:39