BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//CERN//INDICO//EN
BEGIN:VEVENT
SUMMARY:The Wide and Wonderful World of Optimal Transport Theory in Physic
 s [Confirmed]
DTSTART:20260422T180000Z
DTEND:20260422T193000Z
DTSTAMP:20260510T140000Z
UID:indico-event-2265@events.perimeterinstitute.ca
DESCRIPTION:Speakers: Jessica Howard (Kavli Institute for Theoretical Phys
 ics)\n\nOptimal transport (OT) theory\, first conceived to solve problems 
 of moving dirt\, has since evolved into a powerful mathematical framework 
 with far-reaching applications across machine learning\, probability and s
 tatistics\, and theoretical physics. In particle physics\, OT underpins ma
 ny modern machine learning algorithms and data-analysis methods. It also o
 ffers rigorous numerical strategies for non-perturbative field theory calc
 ulations and provides a framework for strengthening the connection between
  field theories and neural networks. In this talk\, I will motivate how OT
  provides a unifying language for connecting ensembles of neural networks\
 , statistical field theories\, and exact renormalization group flows. I wi
 ll highlight how viewing field theories as probability distributions (over
  an infinite dimensional function space) makes OT a natural tool\, offerin
 g both numerical strategies and analytic insights. Additionally\, OT and t
 he renormalization group can be used to better understand feature learning
  and training dynamics in ensembles of asymptotically wide neural networks
 . The goal is not only to showcase the wide and wonderful reach of OT in p
 hysics\, but also to illustrate how it opens new perspectives for tackling
  non-perturbative problems and for deepening the dialogue between physics 
 and machine learning.\n\nhttps://events.perimeterinstitute.ca/event/2265/
LOCATION:PI/2-292 - Time Room (Perimeter Institute for Theoretical Physics
 )
URL:https://events.perimeterinstitute.ca/event/2265/
END:VEVENT
END:VCALENDAR