BEGIN:VCALENDAR
VERSION:2.0
CALSCALE:GREGORIAN
PRODID:UW-Madison-Physics-Events
BEGIN:VEVENT
SEQUENCE:1
UID:UW-Physics-Event-6904
DTSTART:20220504T160000Z
DTEND:20220504T171500Z
DTSTAMP:20241006T011932Z
LAST-MODIFIED:20220415T012034Z
LOCATION:Online Seminar: Please sign up for our mailing list at www.ph
ysicsmeetsml.org for zoom link. We will also livestream the talk in Ch
amberlin 5280.
SUMMARY:Renormalization Group Flow as Optimal Transport\, Physics ∩
ML Seminar\, Semon Rezchikov\, Harvard University
DESCRIPTION:In this talk\, I will describe how the renormalization gro
up (RG)\, a fundamental aspect of statistical in quantum field theory\
, can be cast as a variational problem using ideas from optimal transp
ort. I will review the renormalization group as well as optimal transp
ort for non-specialists. The latter subject is naturally connected to
methods in machine learning. This variational formulation of RG\, beyo
nd having theoretical interest\, can be used to design neural networks
which compute the renormalization group flow of conventional field th
eories. The renormalization group has been fundamental in the design o
f the numerical algorithms for finding ground states and computing phy
sical quantities of 1+1 dimensional field theories which have been suc
cessful thus far. I will discuss the prospects for using this formulat
ion of RG to merge modern techniques from machine learning with ideas
involving renormalization\, in order to tackle fundamental problems in
the study in field theories of dimension greater than 1+1.
URL:https://www.physics.wisc.edu/events/?id=6904
END:VEVENT
END:VCALENDAR