An Efficient Re-Scaled Perceptron Algorithm for Conic Systems
Name
4627-06.pdf
Size
354.63 KB
Format
Adobe PDF
Checksum (MD5)
d1a8d7ffa2d552a234657db27ef80289
Author(s)
Belloni, Alexandre
Freund, Robert M
Vempala, Santosh
Date Issued
April 27, 2007
Series/Report no.
MIT Sloan School of Management Working Paper
4627-06
Abstract
The classical perceptron algorithm is an elementary row-action/relaxation algorithm for solving a homogeneous linear inequality system Ax > 0. A natural condition measure associated with this algorithm is the Euclidean width T of the cone of feasible solutions, and the iteration complexity of the perceptron algorithm is bounded by 1/T^2, see Rosenblatt 1962. Dunagan and Vempala have developed a re-scaled version of the perceptron algorithm with an improved complexity of O(n ln(1/T)) iterations (with high probability), which is theoretically efficient in T, and in particular is polynomial-time in the bit-length model. We explore extensions of the concepts of these perceptron methods to the general homogeneous conic system Ax is an element of a set 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. We give a general condition under which the re-scaled perceptron algorithm is itself theoretically efficient; this includes the cases when K is the cross-product of half-spaces, second-order cones, and the positive semi-definite cone.
Subjects
convex cone
perceptron
conic system
separation oracle
Persistent DSpace Link
