BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//132.216.98.100//NONSGML kigkonsult.se iCalcreator 2.20.4//
BEGIN:VEVENT
UID:20260202T184409EST-9224JP8u5D@132.216.98.100
DTSTAMP:20260202T234409Z
DESCRIPTION:Title: “Gromov-Wasserstein Distances: Computation and Statistic
 s”\n\nAbstract:\n\nIn recent years\, the statistical and computational stu
 dy of optimal transport (OT) has advanced significantly\, driven\, in part
 \, by its broad applicability across data science\, statistics\, economics
 \, and physics. While OT distances\, such as the Wasserstein metric\, are 
 well suited for comparing distributions on the same space and endow the sp
 ace of probabilities on a given space with a rich geometry\, comparing dat
 asets of different types -- such as text and images -- requires specifying
  an ad hoc cost function\, which may fail to capture a meaningful correspo
 ndence between data points. \n\nTo address this limitation\, Gromov-Wasser
 stein (GW) distances have been proposed as a natural extension of the OT f
 ramework for comparing metric measure (mm) spaces based only on their intr
 insic structure. Notably\, GW distances define a metric on the space of al
 l mm spaces and provide a means by which to align them. Despite their broa
 d applicability to comparing heterogeneous datasets\, the statistical and 
 computational study of GW distances remained limited until quite recently.
  \n\nThis talk will outline recent progress in the statistical and computa
 tional study of GW distances and will discuss ongoing and future direction
 s for this line of work. \n\nThis is joint work with Ziv Goldfeld and Keng
 o Kato.\n\n🔗 Zoom: https://mcgill.zoom.us/j/87243623765\n	Meeting ID: 872 4
 362 3765\n
DTSTART:20251128T183000Z
DTEND:20251128T193000Z
LOCATION:Room 1104\, Burnside Hall\, CA\, QC\, Montreal\, H3A 0B9\, 805 rue
  Sherbrooke Ouest
SUMMARY:Gabriel Rioux  (Imperial College London\, UK)
URL:/mathstat/channels/event/gabriel-rioux-imperial-co
 llege-london-uk-369301
END:VEVENT
END:VCALENDAR