BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Memento EPFL//
BEGIN:VEVENT
SUMMARY:Learning Operators
DTSTART:20230307T161500
DTEND:20230307T171500
DTSTAMP:20260408T034459Z
UID:9dbe36dd837d93bccec6a72d8641cb4cb42af962667fe7a6c78920ca
CATEGORIES:Conferences - Seminars
DESCRIPTION:Siddartha Mishra (ETHZ)\nOperators are mapping between infinit
 e-dimensional spaces and arise in a variety of contexts\, particularly in 
 the solution of PDEs. The main aim of this lecture would be to introduce t
 he audience to the rapidly emerging area of operator learning\, i.e.\, mac
 hine learning operators from data. To this end\, we will summarize existin
 g architectures such as DeepONets and Fourier neural operators (FNOs) as w
 ell as describe the newly proposed Convolutional Neural Operators (CNOs). 
 Theoretical error estimates for different operator learning architectures 
 will be mentioned and numerical experiments comparing them described. Seve
 ral open issues regarding operator learning will also be covered. If time 
 permits\, we will describe Neural Inverse operators (NIOs): a machine-lear
 ning architecture for the efficient learning of a class of inverse problem
 s associated with PDEs. 
LOCATION:GA 3 21 https://plan.epfl.ch/?room==GA%203%2021
STATUS:CONFIRMED
END:VEVENT
END:VCALENDAR