BEGIN:VCALENDAR
PRODID:-//Compnay Inc//Product Application//EN
VERSION:2.0
METHOD:PUBLISH
BEGIN:VEVENT
DTSTART:20260715T060000Z
DTEND:20260715T070000Z
DTSTAMP:20260713T014914Z
UID:249eaf22-72a8-4660-a96f-18814ac97a2b
CREATED:20260709T102413Z
X-ALT-DESC;FMTTYPE=text/html:Castle.Proxies.LanguageContentMapProxy
DESCRIPTION:Abstract 
Stochastic Mirror Descent is an elegant optimization framework underlying many machine learning and reinforcement learning algorithms. In this talk, we revisit stochastic mirror descent through the lens of projected dynamical systems in a non-Euclidean geometry. This viewpoint provides a unified analytical approach that naturally accommodates non-convex and non-smooth optimization problems, while also allowing for iterate-dependent Markovian noise, thereby moving beyond the stand...
LAST-MODIFIED:20260713T014914Z
LOCATION:Online seminarzoom meeting details:https://zoom.us/j/95725326841?pwd=8NbhnzQsA6MQM5QYaaJQ97F38beXAF.1
meeting id: 957 2532 6841 passcode: 034116 ...
SEQUENCE:0
STATUS:CONFIRMED
SUMMARY:Stochastic Mirror Descent under Markovian Noise: A Dynamical Systems Perspective with Applications to Reinforcement Learning
TRANSP:OPAQUE
END:VEVENT
END:VCALENDAR