Relax and Localize: From Value to Algorithms

Details Relax and Localize: From Value to Algorithms Relax and Localize: From Value to Algorithms

2012-04-04

arxiv.org/abs/1204.0870v1

Computer Science

Learning

Scientific paper

We show a principled way of deriving online learning algorithms from a minimax analysis. Various upper bounds on the minimax value, previously thought to be non-constructive, are shown to yield algorithms. This allows us to seamlessly recover known methods and to derive new ones. Our framework also captures such "unorthodox" methods as Follow the Perturbed Leader and the R^2 forecaster. We emphasize that understanding the inherent complexity of the learning problem leads to the development of algorithms. We define local sequential Rademacher complexities and associated algorithms that allow us to obtain faster rates in online learning, similarly to statistical learning theory. Based on these localized complexities we build a general adaptive method that can take advantage of the suboptimality of the observed sequence. We present a number of new algorithms, including a family of randomized methods that use the idea of a "random playout". Several new versions of the Follow-the-Perturbed-Leader algorithms are presented, as well as methods based on the Littlestone's dimension, efficient methods for matrix completion with trace norm, and algorithms for the problems of transductive learning and prediction with static experts.

Affiliated with

Also associated with

No associations

Rating

Relax and Localize: From Value to Algorithms 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 Relax and Localize: From Value to Algorithms, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Relax and Localize: From Value to Algorithms will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFWR-SCP-O-31615