A Uniform Lower Error Bound for Half-Space Learning

10 years 2 months ago
A Uniform Lower Error Bound for Half-Space Learning
Abstract. We give a lower bound for the error of any unitarily invariant algorithm learning half-spaces against the uniform or related distributions on the unit sphere. The bound is uniform in the choice of the target half-space and has an exponentially decaying deviation probability in the sample. The technique of proof is related to a proof of the Johnson Lindenstrauss Lemma. We argue that, unlike previous lower bounds, our result is well suited to evaluate the bene…ts of multi-task or transfer learning, or other cases where an expense in the acquisition of domain knowledge has to be justi…ed.
Andreas Maurer, Massimiliano Pontil
Added 14 Mar 2010
Updated 14 Mar 2010
Type Conference
Year 2008
Where ALT
Authors Andreas Maurer, Massimiliano Pontil
Comments (0)