BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:“Squeezing the most out of ridge” - Professor Mark van de Wiel
 \, Amsterdam University Medical Center
DTSTART:20200303T140000Z
DTEND:20200303T150000Z
UID:TALK139465@talks.cam.ac.uk
CONTACT:Alison Quenault
DESCRIPTION:Ridge regression is nowadays regarded as a somewhat old-fashio
 ned technique: most statisticians prefer sparse models\, while machine lea
 rners use non-linear\, multi-layer prediction algorithms. The aim of this 
 talk is to endorse ridge by illustrating its strengths\, from a methodolog
 ical\, computational and applied perspective\, including:\n\nFlexibility (
 in terms of output and type of covariates)\n\nBayesian counterpart facilit
 ates empirical Bayes estimation of penalty parameter(s)\n\nDifferential pe
 nalization for multi-modal (e.g. multi-omics) data\n\nPenalty weights mode
 rated by (external) information on the features: \n\nCo-data\n\nEffective 
 posterior feature selection\n\nComputational efficiency\n\nPerformance in 
 clinical (omics) prediction problems\n\nThese strengths will be illustrate
 d on a cancer multi-omics prediction problem.
LOCATION:Large Seminar Room\, 1st Floor\, Institute of Public Health\, Uni
 versity Forvie Site\, Robinson Way\, Cambridge
END:VEVENT
END:VCALENDAR