Free Online Productivity Tools
i2Speak
i2Symbol
i2OCR
iTex2Img
iWeb2Print
iWeb2Shot
i2Type
iPdf2Split
iPdf2Merge
i2Bopomofo
i2Arabic
i2Style
i2Image
i2PDF
iLatex2Rtf
Sci2ools

COLT

2001

Springer

2001

Springer

The notion of embedding a class of dichotomies in a class of linear half spaces is central to the support vector machines paradigm. We examine the question of determining the minimal Euclidean dimension and the maximal margin that can be obtained when the embedded class has a ﬁnite VC dimension. We show that an overwhelming majority of the family of ﬁnite concept classes of any constant VC dimension cannot be embedded in low-dimensional half spaces. (In fact, we show that the Euclidean dimension must be almost as high as the size of the instance space.) We strengthen this result even further by showing that an overwhelming majority of the family of ﬁnite concept classes of any constant VC dimension cannot be embedded in half spaces (of arbitrarily high Euclidean dimension) with a large margin. (In fact, the margin cannot be substantially larger than the margin achieved by the trivial embedding.) Furthermore, these bounds are robust in the sense that allowing each image half spac...

Related Content

Added |
28 Jul 2010 |

Updated |
28 Jul 2010 |

Type |
Conference |

Year |
2001 |

Where |
COLT |

Authors |
Shai Ben-David, Nadav Eiron, Hans-Ulrich Simon |

Comments (0)