BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Memento EPFL//
BEGIN:VEVENT
SUMMARY:IC Mondays seminars - Bayesian Machine Learning: Theory\, Algorith
 ms\, and Large Scale Applications
DTSTART:20100426T161500
DTSTAMP:20260508T103708Z
UID:b5a4a2decc004f4d9a2261715c8e86e90806e92cbce9ac4519e2ff51
CATEGORIES:Conferences - Seminars
DESCRIPTION:Dr. Matthias Seeger\, University of Saarland\nAbstract\nToday'
 s real world problems of information processing rely on inference and deci
 sion making from uncertain knowledge. Modern science and medicine need aut
 onomous tools for acquisition and sifting of data or experimental planning
 . Bayesian graphical modelling poses hard computational challenges in prac
 tice. Some of these have successfully been addressed in machine learning\,
  calling on ideas from stochastic simulation\, convex optimization\, numer
 ical mathematics\, and graph theory.\n\nI will give an overview of my work
 \, alongside many international coauthors\, on progress in probabilistic m
 achine learning. My contributions range from novel theoretical tools to si
 mplify and sharpen analysis of nonparametric Bayesian methods\, over insig
 hts and development of variational approximate inference techniques\, to r
 ecent milestones in convex relaxations and scalable algorithms for image r
 econstruction models. With the latter\, Bayesian computations can be\nperf
 ormed over full high-resolution image bitmaps for the first time. I will d
 emonstrate how magnetic resonance imaging acquisition patterns can be auto
 nomously optimized driven by this novel Bayesian framework\, resulting in 
 substantially shorter scan times.\n\nBiography\nMatthias Seeger received h
 is CS Diploma degree from Karlsruhe university in 1999 (distinction)\, his
  PhD from Edinburgh university in 2003 (with Christopher Williams). He did
  postdoctoral research at the University of California\, Berkeley (with Mi
 chael Jordan\, Peter Bartlett) and at the Max Planck Institute\, Tuebingen
  (with Bernhard Schoelkopf). At present\, he leads an independent research
  group at the Max Planck Institute and Saarland University\, Saarbruecken\
 , supervising three PhD students. He works on the theory\, algorithmics an
 d scalable implementation of Bayesian technology and probabilistic machine
  learning. He is the author of numerous journal and international conferen
 ce publications\, organized workshops at and served in senior program comm
 ittees of leading international machine learning conferences (NIPS AA area
  chair 2004\, 2010\; UAI 2009\; AISTATS 2010).
LOCATION:INM 202
STATUS:CONFIRMED
END:VEVENT
END:VCALENDAR