BEGIN:VCALENDAR
VERSION:2.0
PRODID:icalendar-ruby
CALSCALE:GREGORIAN
METHOD:PUBLISH
BEGIN:VTIMEZONE
TZID:Europe/Vienna
BEGIN:DAYLIGHT
DTSTART:20250330T030000
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
RRULE:FREQ=YEARLY;BYDAY=-1SU;BYMONTH=3
TZNAME:CEST
END:DAYLIGHT
BEGIN:STANDARD
DTSTART:20251026T020000
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
RRULE:FREQ=YEARLY;BYDAY=-1SU;BYMONTH=10
TZNAME:CET
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20260424T143459Z
UID:67f3874935bd5136678813@ist.ac.at
DTSTART:20250418T110000
DTEND:20250418T120000
DESCRIPTION:Speaker: Fanny Yang\nhosted by Locatello Group\nAbstract: In ma
 ny real-world scenarios\, data arise from diverse and complex environments
  that challenge traditional prediction and estimation methods. This talk e
 xplores potential limitations and benefits when trying to integrate hetero
 geneous data sources to enhance predictive accuracy and treatment effect e
 stimation. In the first part\, we discuss the robustness of invariance-bas
 ed methods when conditions for identifiability are not satisfied and what 
 we can achieve in that setting. In the second part\, we show how one can s
 afely use e.g. foundation models trained on external data to achieve effic
 iency gains. The derived methods in both parts suggest effectiveness on re
 al-world data\, and we're hoping to further explore their usefulness in ot
 her settings in future collaborations.
LOCATION:Office Bldg West / Ground floor / Heinzel Seminar Room (I21.EG.101
 )\, ISTA
ORGANIZER:cfrancois@ist.ac.at
SUMMARY:Fanny Yang: Utilizing heterogeneous environments for prediction and
  estimation
URL:https://talks-calendar.ista.ac.at/events/5688
END:VEVENT
END:VCALENDAR