These pages are maintained
by Amos Storkey
Applications are invited for a fully funded 3 year Microsoft Research PhD studentship 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, and combining Baysesian beliefs of independent agents. 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. The market price are then a probabilistic model in its own right. 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 and statistics, economics, game theory, statistical physics, information theory and numerical analysis to establish both the theoretical basis for machine learning markets and the practical development of them.
See e.g. AISTATS paper on Machine Learning Markets.
This is an opportunity undertake a machine learning PhD study 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.
The project is suitable for a student with a strong mathematical background, economics background or physics background, ideally with a top degree/MSc in Mathematics, Economics, Physics, Engineering, Statistics or Computer Science. Informal enquiries should be addressed to Dr Amos Storkey (a.storkey@ed.ac.uk.) with the subject “Machine Learning Market PhD”. Please attach a CV, a list of courses taken and grades obtained, and a 1-2 page statement of your research drivers: what you fundamentally care about in terms of subject matter and interests.
The studentship involves collaboration with Microsoft Research (MSR), Cambridge. There may be opportunities for paid internships at Microsoft Research, but this is entirely at the discretion of Microsoft Research, Cambridge.
See Amos Storkey's homepage 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. We will accept applicants at any time up to the final cutoff of 28 February 2012, but will make a first assessment after 16 December 2011. We reserve the right to accept exceptionally qualified applicant after the early 16 December deadline.
Formal application must be through the School's normal PhD application process: Go to http://www.ed.ac.uk/schools-departments/informatics/postgraduate/apply. Select the Informatics: Institute for Adaptive and Neural Computation research area, and follow the instructions.
Funding Notes:
This is a fully funded studentship for UK and EU students. We welcome overseas applicants, and can provide funding for EU fees and maintenance for overseas students. The remaining fees component will need to come from another source. Overseas applicants are advised to apply before the standard informatics deadlines and apply for other scholarships. See the fees information pages and Key Dates for further information.
References:
Storkey (2011) Machine Learning Markets. AISTATS 2011