BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//CERN//INDICO//EN
BEGIN:VEVENT
SUMMARY:A non-asymptotic analysis of the single component PLS regression
DTSTART:20260507T090000Z
DTEND:20260507T101500Z
DTSTAMP:20260501T142100Z
UID:indico-event-15983@indico.math.cnrs.fr
DESCRIPTION:Speakers: Clément MARTEAU (University Lyon 1)\n\nThis paper i
 nvestigates some theoretical properties of the Partial Least Square (PLS) 
 method. We focus our attention on the single component case\, that provide
 s a useful framework to understand the underlying mechanism. We provide a 
 non-asymptotic upper bound on the quadratic loss in prediction with high p
 robability in a high dimensional regression context. The bound is attained
  thanks to a preliminary test on the first PLS component. In a second time
 \, we extend these results to the sparse partial least squares (sPLS) appr
 oach. In particular\, we exhibit upper bounds similar to those obtained wi
 th the lasso algorithm\, up to an additional restricted eigenvalue constra
 int on the design matrix. (joint with Luca Castelli (PSPM\, ICJ)\, Irène 
 Gannaz (G-SCOP\\_GROG\, G-SCOP)\nPaper\n\nhttps://indico.math.cnrs.fr/even
 t/15983/
LOCATION:Auditorium 3 (Toulouse School of Economics)
URL:https://indico.math.cnrs.fr/event/15983/
END:VEVENT
END:VCALENDAR