BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Stochastic Analysis &amp\; Algorithms: From numerics for SDEs to L
 angevin algorithms - Sotirios Sabanis (University of Edinburgh)
DTSTART:20240627T140000Z
DTEND:20240627T155000Z
UID:TALK217279@talks.cam.ac.uk
DESCRIPTION:In recent years\, diffusion-based algorithms have gained signi
 ficant popularity due to their extensive application in sampling and non-c
 onvex optimization. These algorithms are frequently conceptualized as nume
 rical schemes for stochastic differential equations (SDEs)\, a perspective
  that enables the utilization of advanced tools from modern probability th
 eory and stochastic analysis for their analysis. We will review critical a
 spects of the analysis of these numerical methods applied to random system
 s\, and will provide important comparisons with stochastic gradient method
 s commonly employed in machine learning and artificial intelligence.
LOCATION:External
END:VEVENT
END:VCALENDAR