Panayotis Mertikopoulos
5
Documents
Présentation
I am a principal researcher at the French National Center for Scientific Research (CNRS), where I am a member of the Inria/LIG research team POLARIS. My research interests are somewhat eclectic, and they span the interface of game theory, learning and optimization, with a special view towards their applications to machine learning, operations research, and network theory. I’m especially interested in the long-run behavior of game-theoretic learning and optimization algorithms and dynamics – whether they converge, at what speed, and/or what type of non-stationary, off-equilibrium behaviors may arise when they do not.
Publications
- 5
- 2
- 2
- 1
- 1
- 1
- 1
- 1
- 2
A stochastic approximation algorithm for stochastic semidefinite programmingProbability in the Engineering and Informational Sciences, 2016, 30 (3 sup), pp.431-454. ⟨10.1017/S0269964816000127⟩
Article dans une revue
hal-01382288v1
|
|
|
Penalty-Regulated Dynamics and Robust Learning Procedures in GamesMathematics of Operations Research, 2015, 40 (3), pp.611-633. ⟨10.1287/moor.2014.0687⟩
Article dans une revue
hal-01235243v1
|
Distributed Optimization in Multi-User MIMO Systems with Imperfect and Delayed InformationISIT '14: Proceedings of the 2014 IEEE International Symposium on Information Theory, 2014, Unknown, Unknown Region
Communication dans un congrès
hal-01382297v1
|
|
Entropy-driven dynamics and robust learning procedures in games[Research Report] RR-8210, INRIA. 2013, pp.33
Rapport
hal-00790815v1
|
|
Distributed Optimization in Multi-User MIMO Systems with Imperfect and Delayed Information[Research Report] RR-8426, INRIA. 2013, pp.19
Rapport
hal-00918762v1
|