BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Memento EPFL//
BEGIN:VEVENT
SUMMARY:Thresholding Based Methods for Robust Learning
DTSTART:20170616T113000
DTEND:20170616T121500
DTSTAMP:20260407T061446Z
UID:77339d456d43d55e4a807e63b6037bd0425b06440b2ef9b2b1f386e4
CATEGORIES:Conferences - Seminars
DESCRIPTION:Prateek Jain\, Microsoft Research\nLearning in presence of out
 liers is a critical problem that can heavily affect performance of the lea
 rning algorithms in practice. In this talk\, we present a general approach
  for learning with outliers\, where we iteratively estimate the model para
 meters with estimated inliers and threshold out point which seems unlikely
  to be generated from the model to obtain more refined set of inliers. We 
 instantiate this general approach for the outlier efficient PCA problem an
 d demonstrate that it leads to nearly optimal solution in O(PCA) computati
 on time.
LOCATION:BC 420 https://plan.epfl.ch/?room==BC%20420
STATUS:CONFIRMED
END:VEVENT
END:VCALENDAR