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:6381@i2m.univ-amu.fr
DTSTART;TZID=Europe/Paris:20210611T143000
DTEND;TZID=Europe/Paris:20210611T153000
DTSTAMP:20241120T201417Z
URL:https://www.i2m.univ-amu.fr/evenements/exploiting-local-regularity-pro
 perties-to-boost-and-expand-safe-screening/
SUMMARY:Emmanuel Soubiès (IRIT\, CNRS\, Toulouse): Exploiting local regula
 rity properties to boost and expand safe-screening
DESCRIPTION:Emmanuel Soubiès: A powerful strategy to boost the performance
  of sparse optimization algorithms is known as safe screening: it allows t
 he early identification of zero coordinates in the solution\, which can th
 en be eliminated to reducethe problem's size and accelerate convergence. I
 n this work\, we extend the existing Gap Safe screening framework by relax
 ing the global strong-concavity assumption on the dual cost function. Inst
 ead\, we exploit local regularity properties\, that is\, strong concavityo
 n well-chosen subsets of the domain. The non-negativity constraint is also
  integrated to the existing framework. Besides making safe screening possi
 ble to a broader class of functions that includes beta-divergences (e.g.\,
  the Kullback-Leibler divergence)\,the proposed approach also improves upo
 n the existing Gap Safe screening rules on previously applicable cases (e.
 g.\, logistic regression).\nJoint work with Cassio Dantas and Cédric Fév
 otte.\nhttps://arxiv.org/abs/2102.10846\n
ATTACH;FMTTYPE=image/jpeg:https://www.i2m.univ-amu.fr/wp-content/uploads/2
 021/04/Emmanuel_Soubies.jpg
CATEGORIES:Séminaire,Signal et Apprentissage
END:VEVENT
BEGIN:VTIMEZONE
TZID:Europe/Paris
X-LIC-LOCATION:Europe/Paris
BEGIN:DAYLIGHT
DTSTART:20210328T030000
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
TZNAME:CEST
END:DAYLIGHT
END:VTIMEZONE
END:VCALENDAR