BEGIN:VCALENDAR
VERSION:2.0
PRODID:www.dresden-science-calendar.de
METHOD:PUBLISH
CALSCALE:GREGORIAN
X-MICROSOFT-CALSCALE:GREGORIAN
X-WR-TIMEZONE:Europe/Berlin
BEGIN:VTIMEZONE
TZID:Europe/Berlin
X-LIC-LOCATION:Europe/Berlin
BEGIN:DAYLIGHT
TZNAME:CEST
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
DTSTART:19810329T030000
RRULE:FREQ=YEARLY;INTERVAL=1;BYMONTH=3;BYDAY=-1SU
END:DAYLIGHT
BEGIN:STANDARD
TZNAME:CET
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
DTSTART:19961027T030000
RRULE:FREQ=YEARLY;INTERVAL=1;BYMONTH=10;BYDAY=-1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
UID:DSC-22624
DTSTART;TZID=Europe/Berlin:20260129T150000
SEQUENCE:1769668789
TRANSP:OPAQUE
DTEND;TZID=Europe/Berlin:20260129T160000
URL:https://www.dresden-science-calendar.de/calendar/en/detail/22624
LOCATION:MPI-CBG\, Pfotenhauerstraße 10801307 Dresden
SUMMARY:Ribot: Beyond independent component analysis: identifiability and a
 lgorithms
CLASS:PUBLIC
DESCRIPTION:Speaker: Alvaro Ribot\nInstitute of Speaker: Harvard University
 \nTopics:\n\n Location:\n  Name: MPI-CBG (MPI-CBG CSBD SR Top Floor (VC))\
 n  Street: Pfotenhauerstraße 108\n  City: 01307 Dresden\n  Phone: +49 351
  210-0\n  Fax: +49 351 210-2000\nDescription: Independent Component Analys
 is (ICA) is a classical method for recovering latent variables with useful
  identifiability properties. However\, full independence is a strong assum
 ption that may not hold in many real-world settings. In this talk\, I will
  discuss how much we can relax the independence assumption without losing 
 identifiability of the model. We show that the weakest such assumption is 
 pairwise mean independence. Our identifiability result is based on a gener
 alization of the spectral theorem from matrices to higher-order tensors\, 
 which implies a unique tensor decomposition of the cumulant tensors arisin
 g in the model. This is joint work with Anna Seigal and Piotr Zwiernik.
DTSTAMP:20260519T055841Z
CREATED:20260127T063559Z
LAST-MODIFIED:20260129T063949Z
END:VEVENT
END:VCALENDAR