Rademacher processes and bounding the risk of function learning

Simple item page
dc.creatorKoltchinskii, Vladimir
dc.creatorPanchenko, Dmitry
dc.date2004-05-17
dc.date.accessioned2026-07-07T05:08:21Z
dc.date.available2026-07-07T05:08:21Z
dc.descriptionWe construct data dependent bounds on the risk in function learning problems. The bounds are based on the local norms of the Rademacher process indexed by the underlying function class and they do not require prior knowledge about the distribution of the training examples or any specific properties of the function class.
dc.description14 pages
dc.identifierhttps://arxiv.org/abs/math/0405338
dc.identifierhttp://arxiv.org/abs/math/0405338
dc.identifier2000 In: High Dimensional Probability II pp. 443 - 459
dc.identifier.urihttp://salesiana.dossiersoluciones.com/handle/123456789/71228
dc.subjectProbability
dc.subject60G35
dc.titleRademacher processes and bounding the risk of function learning
dc.typetext

Files

Collections

arXiv