BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//132.216.98.100//NONSGML kigkonsult.se iCalcreator 2.20.4//
BEGIN:VEVENT
UID:20261118T100622EST-1028MCs9Mc@132.216.98.100
DTSTAMP:20261118T150622Z
DESCRIPTION:Title: Hamilton-Jacobi equations for statistical inference prob
 lems\n\nAbstract: We present the Hamilton--Jacobi equation approach to a c
 lass of high dimensional statistical inference problems. We start by intro
 ducing the model of matrix tensor products\, the free energy associated wi
 th them\, and motivation for studying their high-dimensional limit. Then\,
  we sketch the basic setup of the Hamilton--Jacobi equation approach. Last
 ly\, I discuss the application of this approach to models with multiple hi
 dden layers. This is based on joint work with Hong-Bin Chen\, and Jean-Chr
 istophe Mourrat.\n\nLocation: \n\n(Remote) https://mcgill.zoom.us/j/863143
 28515?pwd=WnBuci9qNVNST3l1OTZUaVNTRlQ0UT09\n
DTSTART:20220309T163000Z
DTEND:20220309T173000Z
SUMMARY:Jiaming Xia (University of Pennsylvania)
URL:https://www.mcgill.ca/mathstat/channels/event/jiaming-xia-university-pe
 nnsylvania-338201
END:VEVENT
END:VCALENDAR
