BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//pretalx//pretalx.com//pyconde-pydata-2026//talk//KLN78E
BEGIN:VTIMEZONE
TZID:CET
BEGIN:STANDARD
DTSTART:20001029T040000
RRULE:FREQ=YEARLY;BYDAY=-1SU;BYMONTH=10
TZNAME:CET
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
END:STANDARD
BEGIN:DAYLIGHT
DTSTART:20000326T030000
RRULE:FREQ=YEARLY;BYDAY=-1SU;BYMONTH=3
TZNAME:CEST
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
END:DAYLIGHT
END:VTIMEZONE
BEGIN:VEVENT
UID:pretalx-pyconde-pydata-2026-KLN78E@pretalx.com
DTSTART;TZID=CET:20260414T122500
DTEND;TZID=CET:20260414T125500
DESCRIPTION:Tabular data\, spreadsheets organized in rows and columns\, are
  ubiquitous across healthcare\, business and finance. The fundamental pred
 iction task of filling in missing values of a label column based on the re
 st of the columns is essential for thousands of use cases of high societal
  and commercial value. While gradient-boosted decision trees have dominate
 d tabular data for the past 20 years\, we demonstrate that this is rapid
 ly changing\, with the foundation model revolution having arrived at tabul
 ar data. We will show the methods behind this and their extensions to caus
 ality\, interpretability and robustness\, and demo various agentic extensi
 ons.
DTSTAMP:20260523T180036Z
LOCATION:Merck Plenary (Spectrum) [1st Floor]
SUMMARY:The foundation model revolution for tabular data - Frank Hutter
URL:https://pretalx.com/pyconde-pydata-2026/talk/KLN78E/
END:VEVENT
END:VCALENDAR