Machine Learning Markets

Applications are invited for 3.5 year PhD in Machine Learning Markets

Machine Learning Markets are a novel state-of-the-art development in probabilistic machine learning involve extending prediction market mechanisms for doing machine learning. They are a meta-modelling approach, and provide principled methods for combining models, building hierarchical models, and deriving new features, through multiple machine learning agents acting in an artificial prediction market, and creating derived goods in that market. Because the markets are robust to new agents joining or leaving, they can continuously improve as modelling capability improves. This PhD will involve integrating ideas from machine learning, economics, game theory, statistical physics, information theory and numerical analysis to establish both the theoretical and practical basis for machine learning markets, including matching market based and physics models for machine learning.

See e.g. http://www.unifr.ch/econophysics/paper/show/id/1106.4509

This is an opportunity to do a machine learning PhD at a world-leading research group in the field. The machine learning group in the Institute for Adaptive and Neural Computation is made up of 6 academic staff: Chris Bishop, Chris Williams, Amos Storkey, Charles Sutton, Guido Sanguinetti, Iain Murray. The group conducts research into the development of novel probabilistic machine learning methods, and the application of these novel methods to cutting edge scientific/technological problems. The School of Informatics, University of Edinburgh is world renowned, and according to all UK Research Assessment Exercises produces the most world leading research of all Computing/Informatics departments in the UK.

Informal enquiries should be addressed to Dr Amos Storkey ([Email Address Removed].) with the subject “Machine Learning Market PhD”.

See http://homepages.inf.ed.ac.uk/amos/ for more information for prospective PhD students. We recommend that students make informal contact a before making a formal application, ideally as soon as possible, but certainly before Dec 1 2012. Formal application must be through the School's normal PhD application process: http://www.ed.ac.uk/schools-departments/informatics/postgraduate/apply Select the Informatics: Institute for Adaptive and Neural Computation research area.