Online Passive-Aggressive Algorithms

Abstract

We present a unified view for online classification, regression, and uni-class problems. This view leads to a single algorithmic framework for the three problems. We prove worst case loss bounds for various algorithms for both the realizable case and the non-realizable case. A conversion of our main online algorithm to the setting of batch learning is also discussed. The end result is new algorithms and accompanying loss bounds for the hinge-loss.

Extracted Key Phrases

3 Figures and Tables

Showing 1-10 of 564 extracted citations
050100'04'05'06'07'08'09'10'11'12'13'14'15'16'17
Citations per Year

949 Citations

Semantic Scholar estimates that this publication has received between 826 and 1,092 citations based on the available data.

See our FAQ for additional information.