BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//wp-events-plugin.com//6.4.6.4.1//EN
TZID:Europe/Paris
X-WR-TIMEZONE:Europe/Paris
BEGIN:VEVENT
UID:3549@i2m.univ-amu.fr
DTSTART;TZID=Europe/Paris:20150109T140000
DTEND;TZID=Europe/Paris:20150109T150000
DTSTAMP:20141225T130000Z
URL:https://www.i2m.univ-amu.fr/events/a-bellet-telecom-paris-the-frank-wo
lfe-algorithm-recent-results-and-applications-to-high-dimensional-similari
ty-learning-and-distributed-optimization/
SUMMARY:A. Bellet (Télécom Paris): The Frank-Wolfe Algorithm: Recent Resu
lts and Applications to High-Dimensional Similarity Learning and Distribut
ed Optimization -
DESCRIPTION:Title: The Frank-Wolfe Algorithm: Recent Results and Applicatio
ns to High-Dimensional Similarity Learning and Distributed Optimization\n\
nAbstract: The topic of this talk is the Frank-Wolfe (FW) algorithm\\\, a
greedy procedure for minimizing a convex and differentiable function over
a compact convex set. FW finds its roots in the 1950's but has recently re
gained a lot of interest in machine learning and related communities. In t
he first part of the talk\\\, I will introduce the FW algorithm and review
some recent results that motivate its appeal in the context of large-scal
e learning problems. In the second part\\\, I will describe two applicatio
ns of FW in my own work: (i) learning a similarity/distance function for s
parse high-dimensional data\\\, and (ii) learning sparse combinations of e
lements that are distributed over a network.\n
END:VEVENT
BEGIN:VTIMEZONE
TZID:Europe/Paris
X-LIC-LOCATION:Europe/Paris
BEGIN:STANDARD
DTSTART:20141026T020000
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
TZNAME:CET
END:STANDARD
END:VTIMEZONE
END:VCALENDAR