The next School Research Seminar will be given by Dr Andrea Lecchini-Visintini, Control Group, Department of Engineering, University of Leicester in Jennison Seminar Room 3 on Thursday, 12th May at 2.30 pm
The seminar will introduce bounds on the finite-time performance of Markov chain Monte Carlo (MCMC) algorithms in solving global stochastic optimization problems defined over continuous domains. It will be shown that MCMC algorithms with finite-time guarantees can be developed with a proper choice of the target distribution and by studying their convergence in total variation norm. A comparison with other state-of-the art methods for solving stochastic programming problems with finite-time guarantees will also be presented.
Please contact Professor Sarah Spurgeon (s.k.spurgeon@kent.ac.uk) for further details.
The seminar will introduce bounds on the finite-time performance of Markov chain Monte Carlo (MCMC) algorithms in solving global stochastic optimization problems defined over continuous domains. It will be shown that MCMC algorithms with finite-time guarantees can be developed with a proper choice of the target distribution and by studying their convergence in total variation norm. A comparison with other state-of-the art methods for solving stochastic programming problems with finite-time guarantees will also be presented.
Please contact Professor Sarah Spurgeon (s.k.spurgeon@kent.ac.uk) for further details.