BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Stochastic approximation with heavy tailed noise - Vivek Borkar (I
 ndian Institute of Technology Bombay)
DTSTART:20240425T104500Z
DTEND:20240425T113000Z
UID:TALK214216@talks.cam.ac.uk
DESCRIPTION:This talk will first review the so-called `ODE' (for `Ordinary
  Differential Equations') approach for the analysis of stochastic approxim
 ation algorithms of which stochastic gradient descent is a special case. U
 sing that as a backdrop\, certain analogous results will be presented for 
 a class of algorithms with heavy tailed noise.\nThis is joint work with V.
  Anantharam of Uni. of California at Berkeley.\n&nbsp\;\n&nbsp\;
LOCATION:External
END:VEVENT
END:VCALENDAR