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

COLT

2007

Springer

2007

Springer

Abstract. The classical perceptron algorithm is an elementary algorithm for solving a homogeneous linear inequality system Ax > 0, with many important applications in learning theory (e.g., [11, 8]). A natural condition measure associated with this algorithm is the Euclidean width of the cone of feasible solutions, and the iteration complexity of the perceptron algorithm is bounded by 1/2 . Dunagan and Vempala [5] have developed a re-scaled version of the perceptron algorithm with an improved complexity of O(n ln(1/)) iterations (with high probability), which is theoretically efficient in , and in particular is polynomialtime in the bit-length model. We explore extensions of the concepts of these perceptron methods to the general homogeneous conic system Ax int K where K is a regular convex cone. We provide a conic extension of the re-scaled perceptron algorithm based on the notion of a deep-separation oracle of a cone, which essentially computes a certificate of strong separation...

Related Content

Added |
14 Aug 2010 |

Updated |
14 Aug 2010 |

Type |
Conference |

Year |
2007 |

Where |
COLT |

Authors |
Alexandre Belloni, Robert M. Freund, Santosh Vempala |

Comments (0)