General Algorithmic Frameworks for Online Problems

Yair Censor, Simeon Reich, Alexander J. Zaslavski

Research output: Contribution to journalArticlepeer-review


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 which depend on general conditions on the iterative step sizes.

Original languageEnglish
Pages (from-to)19-36
Number of pages18
JournalInternational Journal of Pure and Applied Mathematics
Issue number1
StatePublished - 1 Jan 2008


Dive into the research topics of 'General Algorithmic Frameworks for Online Problems'. Together they form a unique fingerprint.

Cite this