BEGIN:VCALENDAR
PRODID:-//eluceo/ical//2.0/EN
VERSION:2.0
CALSCALE:GREGORIAN
BEGIN:VEVENT
UID:www.tcs.tifr.res.in/event/1026
DTSTAMP:20230914T125947Z
SUMMARY:Stochastic Recursive Algorithms: A Markov Chain Perspective
DESCRIPTION:Speaker: Abhishek Gupta (The Ohio State University\nColumbus\,
USA)\n\nAbstract: \nAbstract: Many stochastic optimization and empirical
dynamic programming algorithms have been proposed in the literature that a
pproximates certain deterministic learning algorithms. Examples of such al
gorithms are stochastic gradient descent and empirical value iteration\, e
mpirical Q value iteration\, etc. for discounted or average cost MDPs. We
refer to them as stochastic recursive algorithms\, in which an exact contr
action operator over a Euclidean space is replaced with an approximate iid
random operator at every step of the iteration. These algorithms can be v
iewed within the framework of iterated random maps\, and thus Markov chain
theory can be leveraged to study the convergence properties of these algo
rithms. In the talk\, we will discover some new insights about the converg
ence properties of stochastic recursive algorithms. We complement the theo
retical findings with extensive numerical simulations.\nBio: Abhishek Gup
ta is an assistant professor in the ECE department at The Ohio State Unive
rsity. He completed his PhD in Aerospace Engineering from UIUC in 2014. Hi
s research interests are in stochastic control theory\, probability theory
\, and game theory with applications to transportation markets\, electrici
ty markets\, and cybersecurity of control systems.\n
URL:https://www.tcs.tifr.res.in/web/events/1026
DTSTART;TZID=Asia/Kolkata:20191224T143000
DTEND;TZID=Asia/Kolkata:20191224T153000
LOCATION:A-201 (STCS Seminar Room)
END:VEVENT
END:VCALENDAR