BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//GREYC UMR CNRS 6072 - Groupe de Recherche en Informatique, Image, et Instrumentation de Caen - ECPv5.7.0//NONSGML v1.0//EN
CALSCALE:GREGORIAN
METHOD:PUBLISH
X-WR-CALNAME:GREYC UMR CNRS 6072 - Groupe de Recherche en Informatique, Image, et Instrumentation de Caen
X-ORIGINAL-URL:https://www.greyc.fr
X-WR-CALDESC:évènements pour GREYC UMR CNRS 6072 - Groupe de Recherche en Informatique, Image, et Instrumentation de Caen
BEGIN:VTIMEZONE
TZID:Europe/Paris
BEGIN:DAYLIGHT
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
TZNAME:CEST
DTSTART:20210328T010000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
TZNAME:CET
DTSTART:20211031T010000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTART;TZID=Europe/Paris:20211118T153000
DTEND;TZID=Europe/Paris:20211118T163000
DTSTAMP:20260424T073521
CREATED:20211111T095606Z
LAST-MODIFIED:20230307T085652Z
UID:10641-1637249400-1637253000@www.greyc.fr
SUMMARY:Séminaire IMAGE : Quentin Bertrand (MILA)\, « Hyperparameter selection for high dimensional sparse learning: application to neuro-imaging »
DESCRIPTION:Speaker: \nQuentin Bertrand (https://qb3.github.io/) \nAbstract:\nDue to non-invasiveness and excellent time resolution\, magneto- and electroencephalography (M/EEG) have emerged as tools of choice to monitor brain activity. Reconstructing brain signals from M/EEG measurements is a high dimensional ill-posed inverse problem. Typical estimators of brain signals involve challenging optimization problems\, composed of the sum of a data-fidelity term\, and a sparsity promoting term. Because of their notoriously hard to tune regularization hyperparameters\, sparsity-based estimators are currently not massively used by neuroscientists. \nDuring this talk I will talk about two aspects of the brain source reconstruction problem:\n– State of the art solvers for the source localization problem include coordinate descent\, which is notoriously hard to accelerate in practice. I will introduce an effective way to speed it up in theory and practice.\n– Then I will focus on the hyperparameter selection and investigate hyperparameter optimization. It requires tackling bilevel optimization with nonsmooth inner problems. Such problems are canonically solved using zeros order techniques\, such as grid-search or random-search. I will present a more efficient technique to solve these challenging bilevel optimization problems using first-order methods.
URL:https://www.greyc.fr/event/seminaire-image-quentin-bertrand-mila-hyperparameter-selection-for-high-dimensional-sparse-learning-application-to-neuro-imaging/
LOCATION:En distanciel
CATEGORIES:General,Image,Seminaire Image
END:VEVENT
END:VCALENDAR