0.25
0.5
0.75
1.25
1.5
1.75
2
Competing With Strategies
Published on Aug 09, 20133037 Views
We study the problem of online learning with a notion of regret defined with respect to a set of strategies. We develop tools for analyzing the minimax rates and for deriving regret-minimization algor
Related categories
Chapter list
Competing With Strategies00:00
Online Learning With Strategies00:14
Goals02:11
Minimax Rate02:38
Sequential Rademacher Complexity - 104:10
Sequential Rademacher Complexity - 206:37
Other Sequential Complexity Measures07:23
The Relaxation Mechanism08:16
Sequential Rademacher Relaxation10:04
General Recipe11:07
Example: Map Algorithms - 112:08
Example: Map Algorithms - 213:46
Example: Auto-Regressive Model14:17
Other Examples16:35
Further Directions18:25
Thank You19:39