BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//wp-events-plugin.com//6.4.7.3//EN
TZID:Europe/Paris
X-WR-TIMEZONE:Europe/Paris
BEGIN:VEVENT
UID:3090@i2m.univ-amu.fr
DTSTART;TZID=Europe/Paris:20140214T140000
DTEND;TZID=Europe/Paris:20140214T150000
DTSTAMP:20140130T130000Z
URL:https://www.i2m.univ-amu.fr/events/uniform-stability-and-consistency-f
or-operator-valued-kernel-machines/
SUMMARY:Uniform stability and consistency for Operator valued kernel machin
es -
DESCRIPTION:Operator-valued kernels\, such as multi-task kernels\, are appr
opriate for learning problems with nonscalar outputs like structured outpu
t prediction\, and have interesting properties. For instance\, they are pa
rticularly efficient for dealing with functional data\, and for taking int
o account the structure of the output space. However\, they have received
little attention from the community\, particularly from a theoretical poin
t of vue. We will show that operator-valued kernel regression algorithms
are uniformly stable in the general case of infinite-dimensional output sp
aces. We then derive under mild assumption on the kernel generalization bo
unds of such algorithms\, and we show their consistency even with non Hilb
ert-Schmidt operator-valued kernels.http://pageperso.lif.univ-mrs.fr/~juli
en.audiffren/
END:VEVENT
BEGIN:VTIMEZONE
TZID:Europe/Paris
X-LIC-LOCATION:Europe/Paris
BEGIN:STANDARD
DTSTART:20131027T020000
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
TZNAME:CET
END:STANDARD
END:VTIMEZONE
END:VCALENDAR