Bandit Convex Optimization: sqrt{T} Regret in One Dimension thumbnail
Pause
Mute
Subtitles not available
Playback speed
0.25
0.5
0.75
1
1.25
1.5
1.75
2
Full screen

Bandit Convex Optimization: sqrt{T} Regret in One Dimension

Published on Aug 20, 20151787 Views

We analyze the minimax regret of the adversarial bandit convex optimization problem. Focusing on the one-dimensional case, we prove that the minimax regret is $\widetilde\Theta(\sqrt{T})$ and partiall

Related categories

Chapter list

Bandit Convex Optimization: √T Regret in One Dimension00:00
Bandit Convex Optimization00:08
Previous Results01:34
Main Ideas02:19