– L. Ralaivola (LIF) : online confusion learning and passive-aggressive scheme.
Carte non disponible

Date/heure
Date(s) - 22/11/2012
14 h 00 min - 15 h 00 min

Catégories Pas de Catégories


– L. Ralaivola (LIF) : online confusion learning and passive-aggressive scheme.
Carte non disponible

Date/heure
Date(s) - 22/11/2012
14 h 00 min - 15 h 00 min

Catégories Pas de Catégories


Online confusion learning and passive-aggressive scheme By Liva Ralaivola, LIF. This work provides the first — to the best of our knowledge — analysis of online learning algorithms for multiclass problems when the confusion matrix is taken as a performance measure. The work builds upon recent and elegant results on non- commutative concentration inequalities, i.e. concentration inequalities that apply to matrices, and more precisely to matrix martingales. We do establish generalization bounds for online learning algorithms and show how the theoretical study motivates 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 not having to recourse to any optimization package to implement it.
– L. Ralaivola (LIF) : online confusion learning and passive-aggressive scheme.
Carte non disponible

Date/heure
Date(s) - 22/11/2012
14 h 00 min - 15 h 00 min

Catégories Pas de Catégories


Online confusion learning and passive-aggressive scheme\nBy Liva Ralaivola, LIF.\nThis work provides the first — to the best of our knowledge — analysis of online learning algorithms for multiclass problems when the confusion matrix is taken as a performance measure. The work builds upon recent and elegant results on non- commutative concentration inequalities, i.e. concentration inequalities that apply to matrices, and more precisely to matrix martingales. We do establish generalization bounds for online learning algorithms and show how the theoretical study motivates 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 not having to recourse to any optimization package to implement it.[