Panayotis Mertikopoulos
6
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
- 6
- 6
- 2
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 2
- 1
- 1
|
Multi-agent online optimization with delays: Asynchronicity, adaptivity, and optimismJournal of Machine Learning Research, 2022, 23 (78), pp.1--49
Article dans une revue
hal-03410422v1
|
|
The last-iterate convergence rate of optimistic mirror descent in stochastic variational inequalitiesCOLT 2021 - 34th Annual Conference on Learning Theory, Aug 2021, Boulder, United States. pp.1-32
Communication dans un congrès
hal-03342583v1
|
|
Optimization in open networks via dual averagingCDC 2021 - 60th IEEE Annual Conference on Decision and Control, Dec 2021, Austin, United States. pp.1-7, ⟨10.1109/CDC45484.2021.9683558⟩
Communication dans un congrès
hal-03342395v1
|
|
Explore Aggressively, Update Conservatively: Stochastic Extragradient Methods with Variable Stepsize ScalingNeurIPS '20 - 34th International Conference on Neural Information Processing Systems, Dec 2020, Vancouver / Virtual, Canada. pp.16223--16234
Communication dans un congrès
hal-03002844v1
|
|
On the Convergence of Single-Call Stochastic Extra-Gradient MethodsAdvances in Neural Information Processing Systems, Dec 2019, Vancouver, Canada
Communication dans un congrès
hal-02403555v1
|
|
The rate of convergence of Bregman proximal methods: Local geometry vs. regularity vs. sharpness2023
Pré-publication, Document de travail
hal-04307796v1
|