BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Computational Optimisation Group - ECPv6.15.11//NONSGML v1.0//EN
CALSCALE:GREGORIAN
METHOD:PUBLISH
X-WR-CALNAME:Computational Optimisation Group
X-ORIGINAL-URL:http://optimisation.doc.ic.ac.uk
X-WR-CALDESC:Events for Computational Optimisation Group
REFRESH-INTERVAL;VALUE=DURATION:PT1H
X-Robots-Tag:noindex
X-PUBLISHED-TTL:PT1H
BEGIN:VTIMEZONE
TZID:UTC
BEGIN:STANDARD
TZOFFSETFROM:+0000
TZOFFSETTO:+0000
TZNAME:UTC
DTSTART:20160101T000000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTART;TZID=UTC:20170120T150000
DTEND;TZID=UTC:20170120T150000
DTSTAMP:20260419T054246
CREATED:20170116T143747Z
LAST-MODIFIED:20170116T144626Z
UID:419-1484924400-1484924400@optimisation.doc.ic.ac.uk
SUMMARY:Seminar: Stochastic reformulations of linear systems and efficient randomized algorithms
DESCRIPTION:Title: Stochastic reformulations of linear systems and efficient randomized algorithms\nSpeaker: Dr. Peter Richtarik\nAffiliation: School of Mathematics\, University of Edinburgh\nLocation: Room 217 Huxley Building\nTime: 3:00pm \nAbstract. We propose a new paradigm for solving linear systems. In our paradigm\, the system is reformulated into a stochastic problem\, and then solved with a randomized algorithm. Our reformulation can be equivalently seen as a stochastic optimization problem\, stochastically preconditioned linear system\, stochastic fixed point problem and as a probabilistic intersection problem. We propose and analyze basic\, parallel and accelerated stochastic algorithms for solving the reformulated problem\, with linear convergence rates. \nAbout the speaker. Peter Richtarik is a Reader in the School of Mathematics at the University of Edinburgh\, and is the Head of a Big Data Optimization Lab. He received his PhD from Cornell University in 2007\, and currently holds an EPSRC Early Career Fellowship in Mathematical Sciences. His main research focus is the development of new optimization algorithms and theory. In particular\, much of his recent work is in the emerging field of big data optimization\, with applications in machine learning in general and empirical risk minimization in particular. For big data optimization problems\, traditional methods are no longer suitable\, and hence there is need to develop new algorithmic paradigms. An important role in this respect is played by randomized algorithms of various flavors\, including randomized coordinate descent\, stochastic gradient descent\, randomized subspace descent and randomized quasi-Newton methods. Parallel and distributed variants are of particular importance.
URL:http://optimisation.doc.ic.ac.uk/event/seminar-stochastic-reformulations-of-linear-systems-and-efficient-randomized-algorithms/
END:VEVENT
END:VCALENDAR