Sign inSign up
Online Learning with Feedback Graphs: Beyond Bandits 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

Online Learning with Feedback Graphs: Beyond Bandits

Published on Aug 20, 20151848 Views

Tomer Koren

We study a general class of online learning problems where the feedback is specified by a graph. This class includes online prediction with expert advice and the multi-armed bandit problem, but also s

COLT 2015 - Paris

Related categories

Active LearningComputational Learning TheoryOn-line LearningReinforcement LearningSemi-supervised Learning

Chapter list

Online Learning with Feedback Graphs: Beyond Bandits00:00
Learning with Graph Feedback - 100:12
Learning with Graph Feedback - 200:58
Learning with Graph Feedback - 301:10
Learning with Graph Feedback - 401:38
Learning with Graph Feedback - 501:48
Learning with Graph Feedback - 602:12
Main Result: Characterization02:48
Example - 103:37
Example - 203:54
Example - 304:09
Example - 404:13
Example - 504:57
Example - 604:58
“Apple Tasting”05:41
Full-feedback minus Loops05:53
At the poster ...06:43