Statistics – Machine Learning
Scientific paper
2011-10-28
Statistics
Machine Learning
This is the full version of the paper with the same name that will appear in Advances in Neural Information Processing Systems
Scientific paper
Most methods for decision-theoretic online learning are based on the Hedge algorithm, which takes a parameter called the learning rate. In most previous analyses the learning rate was carefully tuned to obtain optimal worst-case performance, leading to suboptimal performance on easy instances, for example when there exists an action that is significantly better than all others. We propose a new way of setting the learning rate, which adapts to the difficulty of the learning problem: in the worst case our procedure still guarantees optimal performance, but on easy instances it achieves much smaller regret. In particular, our adaptive method achieves constant regret in a probabilistic setting, when there exists an action that on average obtains strictly smaller loss than all other actions. We also provide a simulation study comparing our approach to existing methods.
Erven Tim van
Grunwald Peter
Koolen Wouter M.
Rooij Steven de
No associations
LandOfFree
Adaptive Hedge does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.
If you have personal experience with Adaptive Hedge, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Adaptive Hedge will most certainly appreciate the feedback.
Profile ID: LFWR-SCP-O-686692