Computer Science – Learning
Scientific paper
2010-02-26
Proceedings of the 23rd Annual Conference on Learning Theory (COLT) 2010
Computer Science
Learning
Updates to match final COLT version
Scientific paper
We introduce a new online convex optimization algorithm that adaptively chooses its regularization function based on the loss functions observed so far. This is in contrast to previous algorithms that use a fixed regularization function such as L2-squared, and modify it only via a single time-dependent parameter. Our algorithm's regret bounds are worst-case optimal, and for certain realistic classes of loss functions they are much better than existing bounds. These bounds are problem-dependent, which means they can exploit the structure of the actual problem instance. Critically, however, our algorithm does not need to know this structure in advance. Rather, we prove competitive guarantees that show the algorithm provides a bound within a constant factor of the best possible bound (of a certain functional form) in hindsight.
McMahan Brendan H.
Streeter Matthew
No associations
LandOfFree
Adaptive Bound Optimization for Online Convex Optimization 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 Bound Optimization for Online Convex Optimization, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Adaptive Bound Optimization for Online Convex Optimization will most certainly appreciate the feedback.
Profile ID: LFWR-SCP-O-289125