BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//CERN//INDICO//EN
BEGIN:VEVENT
SUMMARY:Generative AI for Numerical Simulation and Inverse Problems: from 
 Theory to Technology [Hausdorff Colloquium]
DTSTART:20270127T140000Z
DTEND:20270127T153000Z
DTSTAMP:20260903T134500Z
UID:indico-event-1559@math-events.uni-bonn.de
DESCRIPTION:Speakers: Hanno Gottschalk (TU Berlin)\n\nAbstract:\nWe discus
 s applications of generative machine learning in numerical simulation both
  from the theoretical and numerical level. When it comes to learning on da
 ta generated by deterministic systems like turbulent flow\, several amendm
 ents to statistical learning theory have to be taken care of. In particula
 r\, we have to replace the standard assumption of independent and identica
 lly distributed data with ergodicity assumptions for dynamical systems. We
  show that this is possible\, including derivation of convergence rates. L
 oosely based on this conceptual basis\, we present numerical studies on tu
 rbulent flow starting from state snapshots going over to dynamics learned 
 by world models. We furthermore discuss the solution to inverse problems b
 ased on recent diagonal flow matching models and how to combine this with 
 generative simulations into interactive and explainable generative design 
 systems.\nWebsite of the Hausdorff Colloquium\n\nhttps://math-events.uni-b
 onn.de/event/1559/
LOCATION:Endenicher Allee 60/1-016 - Lipschitzsaal (Mathezentrum)
URL:https://math-events.uni-bonn.de/event/1559/
END:VEVENT
END:VCALENDAR