BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//pretalx//pretalx.iacapconf.org//iacap-2026//speaker//Q8BLSK
BEGIN:VTIMEZONE
TZID:US/Central
BEGIN:DAYLIGHT
DTSTART:20250717T000000
TZNAME:CDT
TZOFFSETFROM:-0500
TZOFFSETTO:-0500
END:DAYLIGHT
BEGIN:STANDARD
DTSTART:20251102T020000
RDATE:20261101T020000
TZNAME:CST
TZOFFSETFROM:-0500
TZOFFSETTO:-0600
END:STANDARD
BEGIN:DAYLIGHT
DTSTART:20260308T030000
RDATE:20270314T030000
TZNAME:CDT
TZOFFSETFROM:-0600
TZOFFSETTO:-0500
END:DAYLIGHT
END:VTIMEZONE
BEGIN:VEVENT
SUMMARY:Occam's Razor in Machine Learning (IACAP Simon Award Keynote) - To
 m Sterkenburg
DTSTART;TZID=US/Central:20260717T112000
DTEND;TZID=US/Central:20260717T123000
DTSTAMP:20260726T090826Z
UID:pretalx-iacap-2026-JM3AQY@pretalx.iacapconf.org
DESCRIPTION:I give an overview of my work on Occam's razor\, the methodolo
 gical principle to prefer simplicity in inductive inference. This principl
 e presents us with two philosophical problems: what is simplicity (the pro
 blem of definition)\, and why is it good to prefer it (the problem of just
 ification)? I observe that the mathematical theory of machine learning hol
 ds the promise to answer these problems\, for (versions of) Occam's razor 
 in machine learning\, by (1) giving a formal notion of simplicity and (2) 
 connecting this formal notion of simplicity to formal guarantees of succes
 sful learning. I investigate whether this promise holds good.
LOCATION:Apollo Auditorium
URL:https://pretalx.iacapconf.org/iacap-2026/talk/JM3AQY/
END:VEVENT
END:VCALENDAR