An Efficient Rescaled Perceptron Algorithm for Conic Systems

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 {tau} of the cone of feasible solutions, and the iteration complexity of...

Täydet tiedot

Bibliografiset tiedot
Päätekijät: Vempala, Santosh, Belloni, Alexandre, Freund, Robert Michael
Muut tekijät: Sloan School of Management
Aineistotyyppi: Artikkeli
Kieli:en_US
Julkaistu: Institute for Operations Research and the Management Sciences (INFORMS) 2010
Aiheet:
Linkit:http://hdl.handle.net/1721.1/54782
https://orcid.org/0000-0002-1733-5363