Sign inSign up
Hierarchies of Relaxations for Online Prediction Problems with Evolving Constraints thumbnail
Pause
Mute
Subtitles not available
Playback speed
0.25
0.5
0.75
1
1.25
1.5
1.75
2
Full screen

Hierarchies of Relaxations for Online Prediction Problems with Evolving Constraints

Published on Aug 20, 20151725 Views

Karthik Sridharan

We propose a framework for online prediction with a benchmark defined through an evolving constraint set. We analyze a method based on random playout. While computing the optimal decision in hindsight

COLT 2015 - Paris

Related categories

Active LearningComputational Learning TheoryOn-line LearningReinforcement LearningSemi-supervised Learning

Chapter list

Hierarchies of Relaxations for Online Prediction Problems with Evolving Constraints00:00
Problem Setup - 100:05
Problem Setup - 200:24
Problem Setup - 300:30
Problem Setup - 400:41
Problem Setup - 500:46
Problem Setup - 601:31
Problem Setup - 701:57
Goal02:58
Online Node Clasification - 104:06
Online Node Clasification - 204:26
Online Node Clasification - 304:28
Online Node Clasification - 404:36
Online Node Clasification - 504:43
Online Node Clasification - 604:59
Result05:39
Summary06:06