BEGIN:VCALENDAR
VERSION:2.0
PRODID:icalendar-ruby
CALSCALE:GREGORIAN
METHOD:PUBLISH
BEGIN:VTIMEZONE
TZID:Europe/Vienna
BEGIN:DAYLIGHT
DTSTART:20240331T030000
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
RRULE:FREQ=YEARLY;BYDAY=-1SU;BYMONTH=3
TZNAME:CEST
END:DAYLIGHT
BEGIN:STANDARD
DTSTART:20231029T020000
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
RRULE:FREQ=YEARLY;BYDAY=-1SU;BYMONTH=10
TZNAME:CET
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20260424T143231Z
UID:1700748000@ist.ac.at
DTSTART:20231123T150000
DTEND:20231123T160000
DESCRIPTION:Speaker: Rima Alaifari\nhosted by Marco Mondelli\nAbstract: In 
 operator learning\, it has been observed that proposed models may not beha
 ve as operators when implemented on a computer\, questioning the very esse
 nce of what operator learning should be. We contend that some form of cont
 inuous-discrete equivalence is necessary for an architecture to genuinely 
 learn the underlying operator\, rather than just discretizations of it. Em
 ploying frames\, we introduce the framework of Representation equivalent N
 eural Operator (ReNO) to ensure operations at the continuous and discrete 
 level are equivalent.Joint work with Francesca Bartolucci (TU Delft)\, Emm
 anuel de Bézenac (ETH Zurich)\, Bogdan Raoni (ETH Zurich)\, Roberto Molin
 aro (ETH Zurich)\, Siddhartha Mishra (ETH Zurich).
LOCATION:Mondi 2\, ISTA
ORGANIZER:
SUMMARY:Rima Alaifari: Representation equivalent Neural Operators
URL:https://talks-calendar.ista.ac.at/events/4593
END:VEVENT
END:VCALENDAR