video thumbnail
Pause
Mute
Subtitles not available
Playback speed
0.25
0.5
0.75
1
1.25
1.5
1.75
2
Full screen

On the Complexity of Bandit Linear Optimization

Published on 2015-08-201732 Views

We study the attainable regret for online linear optimization problems with bandit feedback, where unlike the full-information setting, the player can only observe its own loss rather than the full lo

Related categories

Presentation

On the Complexity of Bandit Linear Optimization00:00
Bandit Linear Optimization00:11
Domain W - 100:11
Domain W - 201:48
Domain W - 302:24
Domain W - 402:45
Domain W - 502:48
See Poster for Deatils03:29