Ph.D. position INRIA Lille

A PhD studentship is available in at Sequential Learning
Lab in INRIA Lille, France.
The topic is time series prediction, and non-parametric statistical
analysis of time series.

3 year fully funded position (contract).
The position will start in September 2010. The deadline for applications
will be 1st of May, but interested candidates are encouraged to contact me earlier.

The PhD student will work with Daniil Ryabko ,
and with other members of the SequeL group at INRIA Lille.
SequeL is one of the most dynamic labs at INRIA, with over 20
researchers (including PhD students)
working on both fundamental and practical aspects of sequential learning
from statistical learning, through reinforcement learning, to computer
poker and Go players.
INRIA is France’s leading institution in Computer Science, with over
2800 scientists
employed, of which around 250 in Lille.

Lille is the capital of the north of France, a metropolis with 1 million
with excellent train connection to Brussels (40 min), Paris (1h) and
London (1.5h by train).

The basic problem setup is as follows. There is an unknown stochastic
source of data, generating observations in a sequential fashion. The
data can be anything from stock market observations, to DNA sequences,
to behavioural sequences. There are several learning and inference
problems connected with it, of which the two most basic ones are:
predicting the probabilities of the next observations, and testing
hypotheses about the source (such as independence, homogeneity, etc.)
To solve these problems, one has to consider models of the data.
Different types of data require different models.

The goal is to describe those probabilistic models under which
successful learning is possible, for the inference problems
considered: sequential prediction, and hypothesis testing. This would
eventually lead to an automated modelling algorithms for sequential
learning. The primary goal, however, is to establish a theoretical
understanding of what is possible to learn, in the sequential problems
of interest considered, under which assumptions. More precisely, a data
source is a probability distribution on the set of all possible
sequences of observations, and a model is a set of such probability
distributions. We are interested in identifying the properties of models
which ensure the existence of efficient algorithms that are successful
(e.g. as predictors) given the model.


The successful candidate will have a MSc or equivalent degree in
mathematics or computer science,
with strong background in probability and statistics.
Programming skills will be considered a plus.
The working language in the lab is English.

For further information please email daniil.ryabko(at) ,
with subject -SeqPHD-, joining a CV and a description of interests.

More information (including the application procedure) will soon be
available through