BEGIN:VCALENDAR
VERSION:2.0
PRODID:researchseminars.org
CALSCALE:GREGORIAN
X-WR-CALNAME:researchseminars.org
BEGIN:VEVENT
SUMMARY:Katya Scheinberg (ORIE Cornell)
DTSTART:20210215T143000Z
DTEND:20210215T153000Z
DTSTAMP:20260423T021004Z
UID:OWOS/34
DESCRIPTION:Title: <a href="https://researchseminars.org/talk/OWOS/34/">Co
 mplexity Analysis Framework of Adaptive Optimization Methods via Martingal
 es</a>\nby Katya Scheinberg (ORIE Cornell) as part of One World Optimizati
 on seminar\n\n\nAbstract\nWe will present a very general framework for unc
 onstrained adaptive optimization which encompasses standard methods such a
 s line search and trust region methods that use stochastic function measur
 ements and/or derivatives. In particular\, methods that fall in this frame
 work retain desirable practical features such as step acceptance criterion
 \, trust region adjustment and ability to utilize second order models and 
 enjoy the same convergence rates as their deterministic counterparts. The 
 framework is based on bounding the expected stopping time of a stochastic 
 process\, which satisfies certain assumptions. Thus this framework provide
 s strong convergence analysis under weaker conditions than alternative app
 roaches in the literature. We will conclude with a discussion about some i
 nteresting open questions.\n\nThe address and password of the zoom room of
  the seminar are sent by e-mail on the mailinglist of the seminar one day 
 before each talk\n
LOCATION:https://researchseminars.org/talk/OWOS/34/
END:VEVENT
END:VCALENDAR