BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//wp-events-plugin.com//7.2.3.1//EN
TZID:Europe/Paris
X-WR-TIMEZONE:Europe/Paris
BEGIN:VEVENT
UID:12@i2m.univ-amu.fr
DTSTART;TZID=Europe/Paris:20121122T140000
DTEND;TZID=Europe/Paris:20121122T150000
DTSTAMP:20210303T132504Z
URL:https://www.i2m.univ-amu.fr/evenements/online-confusion-learning-and-p
 assive-aggressive-scheme/
SUMMARY:Liva Ralaivola (LIS\, Aix-Marseille Université): Online confusion 
 learning and passive-aggressive scheme.
DESCRIPTION:Liva Ralaivola: Online confusion learning and passive-aggressiv
 e scheme By Liva Ralaivola\, LIF. This work provides the first — to the 
 best of our knowledge — analysis of online learning algorithms for multi
 class problems when the confusion matrix is taken as a performance measure
 . The work builds upon recent and elegant results on non- commutative conc
 entration inequalities\, i.e. concentration inequalities that apply to mat
 rices\, and more precisely to matrix martingales. We do establish generali
 zation bounds for online learning algorithms and show how the theoretical 
 study motivates the proposition of a new confusion-friendly learning proce
 dure. This learning algorithm\, called COPA (for COnfusion Passive-Aggress
 ive) is a passive- aggressive learning algorithm \; it is shown that the u
 pdate equations for COPA can be computed analytically\, thus allowing the 
 user from not having to recourse to any optimization package to implement 
 it.
ATTACH;FMTTYPE=image/jpeg:https://www.i2m.univ-amu.fr/wp-content/uploads/2
 020/01/Liva_Ralaivola.jpg
CATEGORIES:Séminaire,Signal et Apprentissage
END:VEVENT
BEGIN:VTIMEZONE
TZID:Europe/Paris
X-LIC-LOCATION:Europe/Paris
BEGIN:STANDARD
DTSTART:20121028T020000
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
TZNAME:CET
END:STANDARD
END:VTIMEZONE
END:VCALENDAR