BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Memento EPFL//
BEGIN:VEVENT
SUMMARY:Imaging Seminar: Posterior-Variance-Based Error Quantification for
  Inverse Problems in Imaging
DTSTART:20231116T170000
DTEND:20231116T180000
DTSTAMP:20260406T125530Z
UID:68dcd621561b54800132b096ca28ee04869da7416d18fdd615230e61
CATEGORIES:Conferences - Seminars
DESCRIPTION:Prof. Thomas Pock\, Graz University of Technology\n<< Registr
 ation below >>\n\nAbstract:\nWe present a method for obtaining pixel-wise 
 error bounds in Bayesian regularization of inverse problems in imaging. Th
 e proposed method uses posterior variance estimates together with empirica
 l quantile regularization techniques to obtain coverage guarantees for the
  error bounds without making assumptions about the underlying data distrib
 ution. It is generally applicable to Bayesian regularization approaches\, 
 regardless of the choice of prior data term and sampling algorithms.\n\nBi
 ography:\nThomas Pock received his MSc (1998-2004) and his PhD (2005-2008)
  in Computer Engineering (Telematik) from Graz University of Technology. A
 fter a Post-doc position at the University of Bonn\, he moved back to Graz
  University of Technology where he has been an Assistant Professor at the 
 Institute of Computer Graphics and Vision. In 2013 Thomas Pock received th
 e START price of the Austrian Science Fund (FWF) and the German Pattern re
 cognition award of the German association for pattern recognition (DAGM). 
 In 2014\, he received a starting grant from the European Research Council 
 (ERC). Since 2014 Thomas Pock is a Professor of Computer Science at Graz U
 niversity of Technology\, where he is leading the vision\, learning and op
 timization (VLO) group. In 2019\, he became a member (reporter) of the boa
 rd of the Austrian Science Fund (FWF) for the section computer science. Th
 e focus of his research is image processing\, computer vision\, inverse pr
 oblems\, convex and non-smooth optimization\, and machine learning.\n\nThe
  talk is followed by an aperitif. \nRegistration appreciated\nMore info 
 here\n 
LOCATION:BM 5202 https://plan.epfl.ch/?room==BM%205202
STATUS:CONFIRMED
END:VEVENT
END:VCALENDAR