Online Passive-Aggressive Algorithms

13 years 6 months ago
Online Passive-Aggressive Algorithms
We present a family of margin based online learning algorithms for various prediction tasks. In particular we derive and analyze algorithms for binary and multiclass categorization, regression, uniclass prediction and sequence prediction. The update steps of our different algorithms are all based on analytical solutions to simple constrained optimization problems. This unified view allows us to prove worst-case loss bounds for the different algorithms and for the various decision problems based on a single lemma. Our bounds on the cumulative loss of the algorithms are relative to the smallest loss that can be attained by any fixed hypothesis, and as such are applicable to both realizable and unrealizable settings. We demonstrate some of the merits of the proposed algorithms in a series of experiments with synthetic and real data sets.
Shai Shalev-Shwartz, Koby Crammer, Ofer Dekel, Yor
Added 31 Oct 2010
Updated 31 Oct 2010
Type Conference
Year 2003
Where NIPS
Authors Shai Shalev-Shwartz, Koby Crammer, Ofer Dekel, Yoram Singer
Comments (0)