Here is a list of (funded) interships proposals for the year 2016-2017.
- Prediction with confident expert advice.
- High-Dimension Online Statistical Decision Making.
- Further optimal bandit strategies.
- Upper Confidence Reinforcement Learning with abstraction of states.
These are intended for Master 2 or outstanding Master 1 students, and open the possibility to start a PhD. If you are interested, go ahead and contact me directly.
I also propose PhD topics. The best way for this is to discuss with me. Here are a few examples:
- Sequential prediction of confidence sets for non-stationary signals:
This is a highly theoretical topic, however with huge applicative potential. This topic requires a strong candidate trained in Mathematical Statistics, with focus on Model selection, Information Theory, Concentration inequalities, and Signal Processing. A descent knowledge of a programming language such as Python and some basic machine learning library is a plus.
- Robust max-flow learning for computational sustainability:
This topic is fairly balanced between theory and practice, and is opening a new application domain with huge societal interest. It requires a strong candidate trained in Reinforcement Learning theory and/or Control theory, proficient in Graph theory and having excellent programming skills. Good knowledge of statistical learning is also assumed.
In case you want to apply for a PhD, I strongly encourage you to read (a substantial part of) the following books and lecture notes:
- Prediction Learning ang Games
Nicolo Cesa-Bianchi, and Gábor Lugosi. Cambridge University Press, 2006.
- Pac-Bayesian supervised classification: The thermodynamics of statistical learning
Catoni, Olivier. IMS, 2007.
- Concentration inequalities: A nonasymptotic theory of independence
Stéphane Boucheron, Gábor Lugosi, and Pascal Massart. OUP Oxford, 2013.
- Self-normalized processes: Limit theory and Statistical Applications
Victor H. Peña, Tze Leung Lai, and Qi-Man Shao. Springer Science & Business Media, 2008.
- Algorithms for Reinforcement Learning
Csaba Szepesvári. Synthesis Lectures on Artificial Intelligence and Machine Learning 4.1 (2010): 1-103.
- Statistical Learning Theory and Sequential Prediction
Alexander Rakhlin, Karthik Sridharan
- Concentration of Measure Inequalities in Information Theory, Communications and Coding,
Raginsky, Maxim, and Igal Sason. Now Publishers Inc., 2014.
- Course on Reinforcement Learning