BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//pretalx//pretalx.com//pyconde-pydata-2025//speaker//79EEXA
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-2025-XRHEYZ@pretalx.com
DTSTART;TZID=CET:20250425T105500
DTEND;TZID=CET:20250425T112500
DESCRIPTION:What if we could make the same revolutionary leap for tables th
 at ChatGPT made for text? While foundation models have transformed how we 
 work with text and images\, tabular / structured data (spreadsheets and da
 tabases) - the backbone of economic and scientific analysis - has been lef
 t behind. TabPFN changes this. It's a foundation model that achieves in 2.
 8 seconds what traditional methods need 4 hours of hyperparameter tuning f
 or - while delivering better results. On datasets up to 10\,000 samples\, 
 it outperforms every existing Python library\, from XGBoost to CatBoost to
  Autogluon.\n\nBeyond raw performance\, TabPFN brings foundation model cap
 abilities to tables: native handling of messy data without preprocessing\,
  built-in uncertainty estimation\, synthetic data generation\, and transfe
 r learning - all in a few lines of Python code. Whether you're building ri
 sk models\, accelerating scientific research\, or optimizing business deci
 sions\, TabPFN represents the next major transformation in how we analyze 
 data. Join us to explore and learn how to leverage these new capabilities 
 in your work.
DTSTAMP:20260422T235539Z
LOCATION:Platinum3
SUMMARY:The Foundation Model Revolution for Tabular Data - Noah Hollmann\, 
 Frank Hutter
URL:https://pretalx.com/pyconde-pydata-2025/talk/XRHEYZ/
END:VEVENT
END:VCALENDAR