Post-doctoral positions in theoretical machine learning at Inria Lille

The topic belongs to the areas of machine learning and (extremely) nonparametric statistics. The central theme of this topic is to explore which regularities are "learnable" from data. Specifically, this general question is considered for the problem of forecasting, that is, predicting the probabilities of future outcomes of a series of events given the past. The question to be addressed is: under which assumptions on the stochastic mechanism generating the data is it possible to find the solution to the problem? Various mathematical formulations of this problem are possible. One of them is as follows. The data is generated by a time-series probability measure that is unknown, but is known to belong to a set of measures C. It is required to construct a predictor whose forecasting error converges to 0, as the amount of available data tends to infinity. The question is : under which conditions on C is this possible ?
Background papers :
http://daniil.ryabko.net/ryabko10a.pdf
http://daniil.ryabko.net/ryabko11a.pdf
Skills and profile
Ph.D. in mathematics, statistics or computer science (should be obtained by the starting date). In case the degree is in computer science, strong mathematical background is a must.
Benefits
Possibility of French courses
Help for housing
Financial support from Inria to catering and transportation expenses
Scientific Resident card and help for visa
Additional information
Duration : 16 months
Starting date of the contract : 01/11/2015
Salary : Salary: 2 621 euros gross/month salary
Scientific contact : Daniil Ryabko, daniil.ryabko-AT-inria.fr
Application procedure: Applicants must apply online from the Inria Web site at the following address: (link will be by SRH)
Security and defense procedure: In the interests of protecting its scientific and technological assets, Inria is a restricted-access establishment. Consequently, it follows special regulations for welcoming any person who wishes to work with the institute. The final acceptance of each candidate thus depends on applying this security and defense procedure.