General algorithmic frameworks for online problems

Yair Censor(yairmath.haifa.ac.il)
Simeon Reich(sreichtechunix.technion.ac.il)
Alexander Zaslavski(ajzasltechunix.technion.ac.il)

Abstract: We study general algorithmic frameworks for online learning tasks. These include binary classification, regression, multiclass problems and cost-sensitive multiclass classification. The theorems that we present give loss bounds on the behavior of our algorithms that depend on general conditions on the iterative step sizes.

Keywords: Online learning, general algorithms, classification, regression, multiclass, convex feasibility.

Category 1: Applications -- Science and Engineering (Basic Sciences Applications )

Category 2: Convex and Nonsmooth Optimization (Convex Optimization )

Citation: Technical Report April 17, 2008. International Journal of Pure and Applied Mathematics, accepted for publication.

Download: [PDF]

Entry Submitted: 04/22/2008
Entry Accepted: 04/23/2008
Entry Last Modified: 04/22/2008

Modify/Update this entry