BEGIN:VCALENDAR
VERSION:2.0
PRODID:researchseminars.org
CALSCALE:GREGORIAN
X-WR-CALNAME:researchseminars.org
BEGIN:VEVENT
SUMMARY:Michael Muehlebach (UC Berkeley)
DTSTART:20200701T165000Z
DTEND:20200701T171500Z
DTSTAMP:20260423T040115Z
UID:SciDL/5
DESCRIPTION:Title: <a href="https://researchseminars.org/talk/SciDL/5/">Op
 timization with Momentum: Dynamical\, Control-Theoretic\, and Symplectic P
 erspectives</a>\nby Michael Muehlebach (UC Berkeley) as part of Workshop o
 n Scientific-Driven Deep Learning (SciDL)\n\n\nAbstract\nMy talk will focu
 s on the analysis of accelerated first-order optimization algorithms. I wi
 ll show how the continuous dependence of the iterates with respect to thei
 r initial condition can be exploited to characterize the convergence rate.
  The result establishes criteria for accelerated convergence that are easi
 ly verifiable and applicable to a large class of first-order optimization 
 algorithms. The analysis is not restricted to the convex setting and unifi
 es discrete-time and continuous-time models. It also rigorously explains w
 hy structure-preserving discretization schemes are important for momentum-
 based algorithms.\n
LOCATION:https://researchseminars.org/talk/SciDL/5/
END:VEVENT
END:VCALENDAR