MIT Libraries homeMIT Libraries logoDSpace@MIT

MIT
View Item 
  • DSpace@MIT Home
  • Sloan School of Management
  • Sloan Working Papers
  • View Item
  • DSpace@MIT Home
  • Sloan School of Management
  • Sloan Working Papers
  • View Item
JavaScript is disabled for your browser. Some features of this site may not work without it.

An Efficient Re-Scaled Perceptron Algorithm for Conic Systems

Author(s)
Belloni, Alexandre; Freund, Robert M; Vempala, Santosh
Thumbnail
Download4627-06.pdf (354.6Kb)
Metadata
Show full item record
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.
Date issued
2007-04-27
URI
http://hdl.handle.net/1721.1/37304
Series/Report no.
MIT Sloan School of Management Working Paper4627-06
Keywords
convex cone, perceptron, conic system, separation oracle

Collections
  • Sloan Working Papers

Browse

All of DSpaceCommunities & CollectionsBy Issue DateAuthorsTitlesSubjectsThis CollectionBy Issue DateAuthorsTitlesSubjects

My Account

Login

Statistics

OA StatisticsStatistics by CountryStatistics by Department
MIT Libraries homeMIT Libraries logo

Find us on

Twitter Facebook Instagram YouTube RSS

MIT Libraries navigation

SearchHours & locationsBorrow & requestResearch supportAbout us
PrivacyPermissionsAccessibility
MIT
Massachusetts Institute of Technology
Content created by the MIT Libraries, CC BY-NC unless otherwise noted. Notify us about copyright concerns.