jmlr jmlr2008 jmlr2008-68 jmlr2008-68-reference knowledge-graph by maker-knowledge-mining

68 jmlr-2008-Nearly Uniform Validation Improves Compression-Based Error Bounds


Source: pdf

Author: Eric Bax

Abstract: This paper develops bounds on out-of-sample error rates for support vector machines (SVMs). The bounds are based on the numbers of support vectors in the SVMs rather than on VC dimension. The bounds developed here improve on support vector counting bounds derived using Littlestone and Warmuth’s compression-based bounding technique. Keywords: compression, error bound, support vector machine, nearly uniform


reference text