A Chaining Algorithm for Online Nonparametric Regression
Abstract
We consider the problem of online nonparametric regression with arbitrary deterministic sequences. Using ideas from the chaining technique, we design an algorithm that achieves a Dudleytype regret bound similar to the one obtained in a nonconstructive fashion by Rakhlin and Sridharan (2014). Our regret bound is expressed in terms of the metric entropy in the sup norm, which yields optimal guarantees when the metric and sequential entropies are of the same order of magnitude. In particular our algorithm is the first one that achieves optimal rates for online regression over H{ö}lder balls. In addition we show for this example how to adapt our chaining algorithm to get a reasonable computational efficiency with similar regret guarantees (up to a log factor).
 Publication:

arXiv eprints
 Pub Date:
 February 2015
 DOI:
 10.48550/arXiv.1502.07697
 arXiv:
 arXiv:1502.07697
 Bibcode:
 2015arXiv150207697G
 Keywords:

 Statistics  Machine Learning;
 Computer Science  Machine Learning
 EPrint:
 Published in the proceedings of COLT 2015: http://jmlr.org/proceedings/papers/v40/Gaillard15.html