BEGIN:VCALENDAR
VERSION:2.0
METHOD:PUBLISH
CALSCALE:GREGORIAN
PRODID:-//WordPress - MECv7.33.0//EN
X-ORIGINAL-URL:https://dcn.nat.fau.eu/
X-WR-CALNAME:
X-WR-CALDESC:FAU DCN-AvH. Chair for Dynamics, Control, Machine Learning and Numerics -Alexander von Humboldt Professorship
X-WR-TIMEZONE:Europe/Berlin
BEGIN:VTIMEZONE
TZID:Europe/Berlin
X-LIC-LOCATION:Europe/Berlin
BEGIN:DAYLIGHT
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
TZNAME:CEST
DTSTART:20260329T030000
RRULE:FREQ=YEARLY;BYMONTH=03;BYDAY=-1SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
TZNAME:CET
DTSTART:20261025T020000
RRULE:FREQ=YEARLY;BYMONTH=10;BYDAY=4SU
END:STANDARD
END:VTIMEZONE
REFRESH-INTERVAL;VALUE=DURATION:PT1H
X-PUBLISHED-TTL:PT1H
X-MS-OLK-FORCEINSPECTOROPEN:TRUE
BEGIN:VEVENT
CLASS:PUBLIC
UID:MEC-6e67691b60ed3e4a55935261314dd534@dcn.nat.fau.eu
DTSTART;TZID=Europe/Berlin:20201202T103000
DTEND;TZID=Europe/Berlin:20201202T113000
DTSTAMP:20211020T085045Z
CREATED:20211020
LAST-MODIFIED:20220117
PRIORITY:5
SEQUENCE:0
TRANSP:OPAQUE
SUMMARY:Statistical inverse problems and gradient flow structures in the space of probability measures
DESCRIPTION:Speaker: Prof. Dr. Sebastian Reich\nAffiliation: Universität Potsdam (Germany)\nOrganized by: FAU DCN-AvH, Chair for Dynamics, Control and Numerics – Alexander von Humboldt Professorship at FAU Erlangen-Nürnberg (Germany)\nZoom link\nMeeting ID: 923 1605 7419 | PIN code: 000474\nAbstract. Statistical inverse problems lead to complex optimisation and/or Monte Carlo\nsampling problems. Gradient descent and Langevin samplers are typically examples of widely used algorithms. In my talk, I will present recent results on optimisation and sampling algorithms, which can be viewed as interacting particle systems, and their mean-field limits.\nI will highlight the geometric structure of these mean-field equations within the, so called, Otto\ncalculus, that is, a gradient flow structure in the space of probability measures. An important outcome\nof recent work on the subject are affine invariant formulations, a property shared with Newton’s\nmethod, but not with gradient descent and ordinary Langevin samplers.\nJoint work with Luc Hillairet (Orléans) and Emmanuel Trélat (Paris).\n \n\nJoin this event at LinkedIn\n\n \n
URL:https://dcn.nat.fau.eu/events/statistical-inverse-problems-and-gradient-flow-structures-in-the-space-of-probability-measures/
CATEGORIES:FAU CAA Seminar,FAU DCN-AvH Seminar,Seminar/Talk
ATTACH;FMTTYPE=image/png:https://dcn.nat.fau.eu/wp-content/uploads/CAAseminar-default-wLogo-1.png
END:VEVENT
END:VCALENDAR