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:8048@i2m.univ-amu.fr
DTSTART;TZID=Europe/Paris:20150612T140000
DTEND;TZID=Europe/Paris:20150612T150000
DTSTAMP:20241120T210007Z
URL:https://www.i2m.univ-amu.fr/evenements/yann-guermeur-loria-lorraine-un
 iversite-guaranteed-risk-for-large-margin-multi-category-classifiers/
SUMMARY: (...): Yann Guermeur (LORIA/Lorraine Université): Guaranteed risk
  for large margin multi-category classifiers
DESCRIPTION:: Title: Guaranteed risk for large margin multi-category classi
 fiers\n \nAbstract: In the framework of agnostic learning\\\, the two basi
 c parameters of a multi-class discrimination problem are the sample size m
  and the number of categories C. In 2007\\\, we contributed to the Vapnik-
 Chervonenkis theory of large margin multi-category classifiers by introduc
 ing the appropriate class of generalized Vapnik-Chervonenkis dimensions: t
 he class of gamma-psi-dimensions. The guaranteed risk we derived exhibited
  a suboptimal ln(m) / m^1/2 convergence rate. In 2012\\\, Mohri and his co
 -authors obtained the optimal 1/m^1/2 rate\\\, with a control term growing
  quadratically with C. In this talk\\\, we prove that this result can be i
 mproved upon\\\, by establishing a bound of equal convergence rate and bet
 ter dependency on C\\\, namely a O(C^3/2).
END:VEVENT
BEGIN:VTIMEZONE
TZID:Europe/Paris
X-LIC-LOCATION:Europe/Paris
BEGIN:DAYLIGHT
DTSTART:20150329T030000
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
TZNAME:CEST
END:DAYLIGHT
END:VTIMEZONE
END:VCALENDAR