Timezone: »

Confusion-Based Online Learning and a Passive-Aggressive Scheme
Liva Ralaivola

Tue Dec 04 10:14 AM -- 10:18 AM (PST) @ Harveys Convention Center Floor, CC

This paper provides the first ---to the best of our knowledge--- analysis of online learning algorithms for multiclass problems when the {\em confusion} matrix is taken as a performance measure. The work builds upon recent and elegant results on noncommutative concentration inequalities, i.e. concentration inequalities that apply to matrices, and more precisely to matrix martingales. We do establish generalization bounds for online learning algorithm and show how the theoretical study motivate the proposition of a new confusion-friendly learning procedure. This learning algorithm, called \copa (for COnfusion Passive-Aggressive) is a passive-aggressive learning algorithm; it is shown that the update equations for \copa can be computed analytically, thus allowing the user from having to recours to any optimization package to implement it.

Author Information

Liva Ralaivola (LIF, IUF, Aix-Marseille University, CNRS)

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors