BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Memento EPFL//
BEGIN:VEVENT
SUMMARY:Non-smooth manifold optimization with applications to machine lear
 ning and pattern recognition
DTSTART:20150703T103000
DTSTAMP:20260406T212711Z
UID:805c59a813861ab0502482c4f1b467f9f2b9668cd347262b9c8aefbc
CATEGORIES:Conferences - Seminars
DESCRIPTION:Prof. Michael Bronstein\, USI\nNumerous problems in machine le
 arning are formulated as optimization with manifold constraints\, i.e.\, w
 here the variables are restricted to a smooth submanifold of the search sp
 ace. For example\, optimization on the Grassman manifold comes up in multi
 -view clustering and matrix completion\; Stiefel manifolds arise in eigenv
 alue-\, assignment-\, and Procrustes problems\, compressed sensing\, shape
  correspondence\, manifold learning\, sensor localization\, structural bio
 logy\, and structure from motion recovery\; manifolds of fixed-rank matric
 es appear in maxcut problems and sparse principal component analysis\; and
  oblique manifolds are encountered in problems such as joint diagonalizati
 on and blind source separation.\nIn this talk\, I will present an ADMM-lik
 e method allowing to handle non-smooth manifold-constrained optimization. 
 Our method is generic and not limited to a specific manifold\, is very sim
 ple to implement\, and does not require parameter tuning. I will show exam
 ples of applications from the domains of physics\, computer graphics\, and
  machine learning.\nBio: Prof. Michael Bronstein was born in 1980. He rece
 ived the B.Sc. summa cum laude from the Department of Electrical Engineeri
 ng in 2002 and Ph.D. with distinction from the Department of Computer Scie
 nce\, Technion in 2007. In 2010\, he has joined the Institute of Computati
 onal Science in the Faculty of Informatics at the University of Lugano (US
 I)\, Switzerland. Since 2012\, he also serves as research scientist at the
  Perceptual Computing lab at Intel. He also held visiting appointments at 
 Politecnico di Milano (2008)\, Stanford university (2009)\, INRIA (2009)\,
  Technion (2013\, 2014)\, and the University of Verona (2010\, 2014). His 
 main research interests are theoretical and computational methods in spect
 ral and metric geometry and their application to problems in computer visi
 on\, pattern recognition\, shape analysis\, computer graphics\, image proc
 essing\, and machine learning.
LOCATION:INF119
STATUS:CONFIRMED
END:VEVENT
END:VCALENDAR