Graduate Seminars

back Back to all Graduate Seminars

CS Graduate Seminar: Randomized projection methods for convex feasibility problems

Start Date: April 16, 2018
End Date: April 16, 2018

By Professor Peter Richtárik (KAUST)
Finding a point in the intersection of a collection of closed convex sets, that is the convex feasibility problem, represents the main modelling strategy for many computational problems. In this paper, we propose new stochastic reformulations of the convex feasibility problem in order to facilitate the development of new randomized algorithmic schemes. We introduce a general randomized projection algorithm and analyse its convergence. Our general random projection algorithm allows to project simultaneously on several sets, thus providing flexibility in matching the implementation of the algorithm on the parallel architecture at hand. Based on the conditioning parameters, besides the asymptotic convergence results, we also derive explicit sublinear and linear convergence rates.
Biography: Peter Richtárik is an Associate Professor of Computer Science and Mathematics at KAUST. He is an EPSRC Fellow in Mathematical Sciences, Fellow of the Alan Turing Institute, and is affiliated with the Visual Computing Center and the Extreme Computing Research Center at KAUST. Dr. Richtarik received his PhD from Cornell University in 2007, and then worked as a Postdoctoral Fellow in Louvain, Belgium, before joining Edinburgh in 2009, and KAUST in 2017. Dr. Richtarik's research interests lie at the intersection of mathematics, computer science, machine learning, optimization, numerical linear algebra, high performance computing and applied probability. Through his recent work on randomized decomposition algorithms (such as randomized coordinate descent methods, stochastic gradient descent methods and their numerous extensions, improvements and variants), he has contributed to the foundations of the emerging field of big data optimization, randomized numerical linear algebra, and stochastic methods for empirical risk minimization. Several of his papers attracted international awards, including the SIAM SIGEST Best Paper Award and the IMA Leslie Fox Prize (2nd prize, three times). He is the founder and organizer of the Optimization and Big Data workshop series. Website:

More Information:

For more info contact: Professor Peter Richtárik: email:
Date: Monday 16th Apr 2018
Time:12:00 PM - 01:00 PM
Location: Building 9, Lecture Hall I Room 2322
Refreshments: Light Lunch will be available at 11:45 AM