P. M. Long. Improved bounds about on-line learning
of smooth functions of a single variable. Theoretical
Computer Science, 241(1-2):25-35, 2000.
(Available in Postscript and PDF formats.)
Abstract
We establish improved bounds on the complexity of
learning classes of smooth functions formed by bounding
different norms of a function's derivative.
The learning model is the generalization of the
mistake-bound model to
continuous-valued functions.