Panayotis Mertikopoulos' homepage

Welcome!


[Page undergoing reconstruction, check back later]


I am an applied mathematician working at the interface of game theory, learning and optimization, with a special view toward 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.

If you are interested in my background, you can visit my bio page or download my CV (this version: Jan. 2023).

For my papers and research, go to my publications page (yes, no prizes for imaginative naming there).

If you wish to contact me, you can reach me via e-mail at: firstname.lastname @ imag.fr


Openings:


There are some prospective openings for people interested in pursuing a PhD or a post-doc on the mathematical side of game theory and optimization, with a view toward their applications to robust machine learning. If you feel like getting your hands dirty, let’s talk!


Hot Stuff:


Grenoble will be hosting the 2023 Alpine Game Theory Symposium, from June 26 to June 30, 2023. This is going to be a week-long conference with ca. 40 plenary talks on all aspects of game theory (mathematical, economic, algorithmic, etc.). It will be a great opportunity to track some of the most recent advances in game theory and related fields - so mark your calendars!


News & Olds:


Biographical information

For the bullet-point version: see my CV.


As an undergrad, I majored in physics at the University of Athens. After graduating in 2003, I enrolled in the graduate program of the Mathematics Department of Brown University. While there, I worked on differential geometry with George Daskalopoulos and I got my M.Sc. and M.Phil. in Mathematics in 2005 and 2006 respectively.

My interests subsequently shifted to applied mathematics and theoretical computer science, so I returned to the University of Athens where I started my PhD with Aris Moustakas. During my PhD, I worked on the applications of game theory to network science and I completed my thesis on “Stochastic perturbations in game theory and applications to networks” in 2010. Subsequently, I spent 2010–2011 as a post-doc at the École Polytechnique in Paris, working on game theory and learning with Rida Laraki.

Since 2011, I have been affiliated with the French National Center for Scientific Research (most recently as a research director in the joint Inria/LIG team POLARIS), as a visiting scholar / professor at the LUISS University of Rome, UC Berkeley, EPFL and NKUA, and as a collaborating senior researcher at the Archimedes Research Center.

In 2019, I completed my Habilitation à Diriger des Recherches (HDR) on “Online optimization and learning in games: Theory and Applications”. If you are curious, you can find here the transcript of my public defense and the referee reports by Jérôme Bolte, Nicolò Cesa-Bianchi, and Sylvain Sorin (to whom I am deeply indebted for their time).

My recent work revolves around game theory, optimization, and their applications to machine learning, operations research, and data science… and I’m still as liable as ever to drop what I’m doing when faced with a cute little problem!


Figure: The long-run behavior of the exponential weights algorithm in different games (click plot to replay). The theory can be found here.

Publications

Any software on this page is distributed “as is” under the GNU general public license. TL;DR: use at will, let me know if you want to modify the source code, don’t sue me if your computer explodes :-)

Copyrights of the published versions of the papers below belong to the publishers. Essentially, this means that publishing houses get to overcharge academic institutions for access to their employees' research, even though all the work has been carried out, reviewed and edited with no cost to the publishers.

If you want to learn more about this ridiculous system, this 2017 long read by the Guardian has a ton of information on the topic.

If you’re wondering about the numbering scheme, “W” is for working papers and preprints, “J” is for journals, “C” for conference proceedings, “S” for software, and “D” for dissertations. Publications are sorted in (roughly) reverse chronological order, but you can also navigate the various tags to see a list of publications by year, venue, or topic. You can also visit my Google Scholar page or my author pages on arXiv and HAL.

Some papers that received a distinction of one form another can be found here.


[J41] - A unified stochastic approximation framework for learning in games
P. Mertikopoulos, Y.-P. Hsieh, and V. Cevher. Mathematical Programming, ser. B, vol. 203, pp. 559-609, January 2024.

[W10] - Setwise coordinate descent for dual asynchronous decentralized optimization
M. Costantini, N. Liakopoulos, P. Mertikopoulos, and T. Spyropoulos. Working paper.

[W9] - Learning in quantum games
K. Lotidis, P. Mertikopoulos, and N. Bambos. Working paper.

[J40] - Multi-agent online learning in time-varying games
B. Duvocelle, P. Mertikopoulos, M. Staudigl, and D. Vermeulen. Mathematics of Operations Research, vol. 48, no. 2, pp. 914-941, May 2023.

[C89] - A quadratic speedup in finding Nash equilibria of quantum zero-sum games
F. Vasconcelos, E. V. Vlatakis-Gkaragkounis, P. Mertikopoulos, and Georgios Piliouras and Michael I. Jordan. In QTML '23: Quantum Techniques in Machine Learning, 2023.

[C88] - The equivalence of dynamic and strategic stability under regularized learning in games
V. Boone and P. Mertikopoulos. In NeurIPS '23: Proceedings of the 37th International Conference on Neural Information Processing Systems, 2023.

[C87] - Riemannian stochastic optimization methods avoid strict saddle points
Y.-P. Hsieh, M. R. Karimi, A. Krause, and P. Mertikopoulos. In NeurIPS '23: Proceedings of the 37th International Conference on Neural Information Processing Systems, 2023.

[C86] - Payoff-based learning with matrix multiplicative weights in quantum games
K. Lotidis, P. Mertikopoulos, N. Bambos, and J. H. Blanchet. In NeurIPS '23: Proceedings of the 37th International Conference on Neural Information Processing Systems, 2023.

[C85] - Exploiting hidden structures in non-convex games for convergence to Nash equilibrium
I. Sakos, E. V. Vlatakis-Gkaragkounis, P. Mertikopoulos, and G. Piliouras. In NeurIPS '23: Proceedings of the 37th International Conference on Neural Information Processing Systems, 2023.

[C84] - The stability of matrix multiplicative weights dynamics in quantum games
K. Lotidis, P. Mertikopoulos, and N. Bambos. In CDC '23: Proceedings of the 62nd IEEE Annual Conference on Decision and Control.

[J39] - Survival of dominated strategies under imitation dynamics
P. Mertikopoulos and Y. Viossat. Journal of Dynamics and Games, W. H. Sandholm memorial issue, vol. 9, no. 4, pp. 499-528, October 2022.

[J38] - Learning in nonatomic games, Part I: Finite action spaces and population games
S. Hadikhanloo, R. Laraki, P. Mertikopoulos, and S. Sorin. Journal of Dynamics and Games, W. H. Sandholm memorial issue, vol. 9, no. 4, pp. 433-460, October 2022.

[J37] - Distributed stochastic optimization with large delays
Z. Zhou, P. Mertikopoulos, N. Bambos, P. W. Glynn, and Y. Ye. Mathematics of Operations Research, vol. 47, no. 3, pp. 2082-2111, August 2022.

[J36] - Multi-agent online optimization with delays: Asynchronicity, adaptivity, and optimism
Y.-G. Hsieh, F. Iutzeler, J. Malick, and P. Mertikopoulos. Journal of Machine Learning Research, vo. 23, no. 78, pp. 1–49, May 2022.

[J35] - Online reconfiguration of IoT applications in the Fog: The information-coordination trade-off
B. Donassolo, A. Legrand, P. Mertikopoulos, and I. Fajjari. IEEE Transactions on Parallel and Distributed Systems, vol. 33, no. 5, pp. 1156–1172, May 2022.

[C83] - On the convergence of policy gradient methods to Nash equilibria in general stochastic games
A. Giannou, K. Lotidis, P. Mertikopoulos, and E. V. Vlatakis-Gkaragkounis. In NeurIPS '22: Proceedings of the 36th International Conference on Neural Information Processing Systems, 2022.

[C82] - No-regret learning in games with noisy feedback: Faster rates and adaptivity via learning rate separation
Y.-G. Hsieh, K. Antonakopoulos, V. Cevher, and P. Mertikopoulos. In NeurIPS '22: Proceedings of the 36th International Conference on Neural Information Processing Systems, 2022.

[C81] - Pick your neighbor: Local Gauss-Southwell rule for fast asynchronous decentralized optimization
M. Costantini, N. Liakopoulos, P. Mertikopoulos, and T. Spyropoulos. In CDC '22: Proceedings of the 61st IEEE Annual Conference on Decision and Control, 2022.

[C80] - Learning in games with quantized payoff observations
K. Lotidis, P. Mertikopoulos, and N. Bambos. In CDC '22: Proceedings of the 61st IEEE Annual Conference on Decision and Control, 2022.

[C79] - Online convex optimization in wireless networks and beyond: The feedback-performance trade-off
E. V. Belmega, R. Negrel, and P. Mertikopoulos. In RAWNET '22: Proceedings of the 18th Workshop on Resource Allocation, Cooperation and Competition in Wireless Networks.

[C78] - AdaGrad avoids saddle points
K. Antonakopoulos, P. Mertikopoulos, G. Piliouras, and X. Wang. In ICML '22: Proceedings of the 39th International Conference on Machine Learning, 2022.

[C77] - UnderGrad: A universal black-box optimization method with almost dimension-free convergence rate guarantees
K. Antonakopoulos, D. Q. Vu, V. Cevher, K. Y. Levy, and P. Mertikopoulos. In ICML '22: Proceedings of the 39th International Conference on Machine Learning, 2022.

[C76] - Nested bandits
M. Martin, P. Mertikopoulos, T. Rahier, and H. Zenati. In ICML '22: Proceedings of the 39th International Conference on Machine Learning, 2022.

[C75] - The dynamics of Riemannian Robbins-Monro algorithms
M. R. Karimi, Y.-P. Hsieh, P. Mertikopoulos, and A. Krause. In COLT '22: Proceedings of the 35th Annual Conference on Learning Theory, 2022.

[C74] - Asymptotic degradation of linear regression estimates with strategic data sources
B. Roussillon, N. Gast, P. Loiseau, and P. Mertikopoulos. In ALT '22: Proceedings of the 33rd International Conference on Algorithmic Learning Theory, 2022.

[J34] - Minibatch forward-backward-forward methods for solving stochastic variational inequalities
R. I. Bot, P. Mertikopoulos, M. Staudigl, and P. T. Vuong. Stochastic systems, vol. 11, no. 2, pp. 112-139, June 2021.

[J33] - Robust power management via learning and game design
Z. Zhou, P. Mertikopoulos, A. L. Moustakas, N. Bambos, and P. W. Glynn. Operations Research, vol. 69, no. 1, pp. 331–345, January 2021.

[C73] - Fast routing under uncertainty: Adaptive learning in congestion games with exponential weights
D. Q. Vu, K. Antonakopoulos, and P. Mertikopoulos. In NeurIPS '21: Proceedings of the 35th International Conference on Neural Information Processing Systems, 2021.

[C72] - The convergence rate of regularized learning in games: From bandits and uncertainty to optimism and beyond
A. Giannou, E. V. Vlatakis-Gkaragkounis, and P. Mertikopoulos. In NeurIPS '21: Proceedings of the 35th International Conference on Neural Information Processing Systems, 2021.

[C71] - Sifting through the noise: Universal first-order methods for stochastic variational inequalities
K. Antonakopoulos, T. Pethick, A. Kavis, P. Mertikopoulos, and V. Cevher. In NeurIPS '21: Proceedings of the 35th International Conference on Neural Information Processing Systems, 2021.

[C70] - Adaptive first-order methods revisited: Convex optimization without Lipschitz requirements
K. Antonakopoulos, and P. Mertikopoulos. In NeurIPS '21: Proceedings of the 35th International Conference on Neural Information Processing Systems, 2021.

[C69] - Equilibrium tracking and convergence in dynamic games
P. Mertikopoulos and M. Staudigl. In CDC '21: Proceedings of the 60th IEEE Annual Conference on Decision and Control.

[C68] - Optimization in open networks via dual averaging
Y.-G. Hsieh, F. Iutzeler, J. Malick, and P. Mertikopoulos. In CDC '21: Proceedings of the 60th IEEE Annual Conference on Decision and Control.

[C67] - Adaptive learning in continuous games: Optimal regret bounds and convergence to Nash equilibrium
Y.-G. Hsieh, K. Antonakopoulos, and P. Mertikopoulos. In COLT '21: Proceedings of the 34th Annual Conference on Learning Theory, 2021.

[C66] - Survival of the strictest: Stable and unstable equilibria under regularized learning with partial information
A. Giannou, E. V. Vlatakis-Gkaragkounis, and P. Mertikopoulos. In COLT '21: Proceedings of the 34th Annual Conference on Learning Theory, 2021.

[C65] - The last-iterate convergence rate of optimistic mirror descent in stochastic variational inequalities
W. Azizian, F. Iutzeler, J. Malick, and P. Mertikopoulos. In COLT '21: Proceedings of the 34th Annual Conference on Learning Theory, 2021.

[C64] - The limits of min-max optimization algorithms: Convergence to spurious non-critical sets
Y.-P. Hsieh, P. Mertikopoulos, and V. Cevher. In ICML '21: Proceedings of the 38th International Conference on Machine Learning, 2021.

[C63] - Zeroth-order non-convex learning via hierarchical dual averaging
A. Héliou, M. Martin, P. Mertikopoulos, and T. Rahier. In ICML '21: Proceedings of the 38th International Conference on Machine Learning, 2021.

[C62] - Regret minimization in stochastic non-convex learning via a proximal-gradient approach
N. Hallak, P. Mertikopoulos, and V. Cevher. In ICML '21: Proceedings of the 38th International Conference on Machine Learning, 2021.

[C61] - Adaptive extra-gradient methods for min-max optimization and games
K. Antonakopoulos, E. V. Belmega, and P. Mertikopoulos. In ICLR '21: Proceedings of the 2021 International Conference on Learning Representations, 2021.

[W5] - Quick or cheap? Breaking points in dynamic markets
P. Mertikopoulos, H. H. Nax, and B. S. R. Pradelski. Working paper.

[J32] - Fast optimization with zeroth-order feedback in distributed multi-user MIMO systems
O. Bilenne, P. Mertikopoulos, and E. V. Belmega. IEEE Transactions on Signal Processing, vol. 68, pp. 6085-6100, October 2020.

[J31] - On the convergence of mirror descent beyond stochastic convex programming
Z. Zhou, P. Mertikopoulos, N. Bambos, S. Boyd, and P. W. Glynn. SIAM Journal on Optimization, vol. 30, no. 1, pp. 687-716, March 2020.

[J30] - When is selfish routing bad? The price of anarchy in light and heavy traffic
R. Colini-Baldeschi, R. Cominetti, P. Mertikopoulos, and M. Scarsini. Operations Research, vol. 68, no. 2, pp. 411–434, March 2020.

[C60] - On the almost sure convergence of stochastic gradient descent in non-convex problems
P. Mertikopoulos, N. Hallak, A. Kavis, and V. Cevher. In NeurIPS '20: Proceedings of the 34th International Conference on Neural Information Processing Systems, 2020.

[C59] - No-regret learning and mixed Nash equilibria: They do not mix
L. Flokas, E. V. Vlatakis-Gkaragkounis, T. Lianeas, P. Mertikopoulos, and G. Piliouras. In NeurIPS '20: Proceedings of the 34th International Conference on Neural Information Processing Systems, 2020.

[C58] - Online non-convex optimization with imperfect feedback
A. Héliou, M. Martin, P. Mertikopoulos, and T. Rahier. In NeurIPS '20: Proceedings of the 34th International Conference on Neural Information Processing Systems, 2020.

[C57] - Explore aggressively, update conservatively: Stochastic extragradient methods with variable stepsize scaling
Y.-G. Hsieh, F. Iutzeler, J. Malick, and P. Mertikopoulos. In NeurIPS '20: Proceedings of the 34th International Conference on Neural Information Processing Systems, 2020.

[C56] - A new regret analysis for Adam-type algorithms
A. Alacaoglu, Y. Malitsky, P. Mertikopoulos, and V. Cevher. In ICML '20: Proceedings of the 37th International Conference on Machine Learning, 2020.

[C55] - Gradient-free online learning in continuous games with delayed rewards
A. Héliou, P. Mertikopoulos, and Z. Zhou. In ICML '20: Proceedings of the 37th International Conference on Machine Learning, 2020.

[C54] - Finite-time last-iterate convergence for multi-agent learning in games
T. Lin, Z. Zhou, P. Mertikopoulos, and M. I. Jordan. In ICML '20: Proceedings of the 37th International Conference on Machine Learning, 2020.

[C53] - Quick or cheap? Breaking points in dynamic markets
P. Mertikopoulos, H. H. Nax, and B. Pradelski. In EC '20: Proceedings of the 21st ACM Conference on Economics and Computation, 2020.

[C52] - Derivative-free optimization over multi-user MIMO networks
O. Bilenne, P. Mertikopoulos, and E. V. Belmega. In NetGCoop '20: Proceedings of the 2020 International Conference on Network Games, Control and Optimization, 2020.

[C51] - Online and stochastic optimization beyond Lipschitz continuity: A Riemannian approach
K. Antonakopoulos, E. V. Belmega, and P. Mertikopoulos. In ICLR '20: Proceedings of the 2020 International Conference on Learning Representations, 2020.

[D3] - Online optimization and learning in games: Theory and applications
P. Mertikopoulos. Habilitation à diriger des recherches (HDR) en Informatique et Mathématiques Appliquées, Université Grenoble Alpes, 2019.

[J29] - Hessian barrier algorithms for linearly constrained optimization problems
I. M. Bomze, P. Mertikopoulos, W. Schachinger, and M. Staudigl. SIAM Journal on Optimization, vol. 29, no. 3, pp. 2100-2127, September 2019.

[J28] - Online power optimization in feedback-limited, dynamic and unpredictable IoT networks
A. Marcastel, E. V. Belmega, P. Mertikopoulos, and I. Fijalkow. IEEE Transactions on Signal Processing, vol. 67, no. 11, pp. 2987-3000, June 2019.

[J27] - Learning in games with continuous action sets and unknown payoff functions
P. Mertikopoulos and Z. Zhou. Mathematical Programming, ser. A, vol. 173, no. 1-2, pp. 465-507, January 2019.

[C50] - On the convergence of single-call stochastic extra-gradient methods
Y.-G. Hsieh, F. Iutzeler, J. Malick, and P. Mertikopoulos. In NeurIPS '19: Proceedings of the 33rd International Conference on Neural Information Processing Systems, 2019.

[C49] - An adaptive mirror-prox algorithm for variational inequalities with singular operators
K. Antonakopoulos, E. V. Belmega, and P. Mertikopoulos. In NeurIPS '19: Proceedings of the 33rd International Conference on Neural Information Processing Systems, 2019.

[C48] - Convergent noisy forward-backward-forward algorithms in non-monotone variational inequalities
M. Staudigl and P. Mertikopoulos. In LSS '19: Proceedings of the 15th IFAC Symposium on Large Scale Complex Systems, 2019.

[C47] - Gradient-free online resource allocation algorithms for dynamic wireless networks
A. Marcastel, E. V. Belmega, P. Mertikopoulos, and I. Fijalkow. In SPAWC '19: Proceedings of the 2019 IEEE International Workshop on Signal Processing Advances in Wireless Communications, 2019.

[C46] - Cautious regret minimization: Online optimization with long-term budget constraints
N. Liakopoulos, A. Destounis, G. Paschos, A. Spyropoulos, and P. Mertikopoulos. In ICML '19: Proceedings of the 36th International Conference on Machine Learning, 2019.

[C45] - Load-aware provisioning of IoT services on Fog computing platforms
B. Donassolo, I. Fajjari, A. Legrand, and P. Mertikopoulos. In ICC '19: Proceedings of the 2019 IEEE International Conference on Communications, 2019.

[C44] - Optimistic mirror descent in saddle-point problems: Going the extra (gradient) mile
P. Mertikopoulos, B. Lecouat, H. Zenati, C.-S. Foo, V. Chandrasekhar, and G. Piliouras. In ICLR '19: Proceedings of the 2019 International Conference on Learning Representations, 2019.

[C43] - Large-scale network utility maximization: Countering exponential growth with exponentiated gradients
L. Vigneri, G. Paschos, and P. Mertikopoulos. In INFOCOM ’19: Proceedings of the 38th IEEE International Conference on Computer Communications, 2019.

[C42] - A Fog-based framework for IoT service provisioning
B. Donassolo, I. Fajjari, A. Legrand, and P. Mertikopoulos. In CCNC '19: Proceedings of the 16th IEEE International Conference on Consumer Communications & Networking, 2019.

[W4] - Multi-agent online learning with imperfect information
Z. Zhou, P. Mertikopoulos, N. Bambos, P. W. Glynn, and C. Tomlin. Working paper.

[J26] - Stochastic mirror descent dynamics and their convergence in monotone variational inequalities
P. Mertikopoulos and M. Staudigl. Journal of Optimization Theory and Applications, vol. 179, no. 3, pp 838-867, December 2018.

[J25] - Riemannian game dynamics
P. Mertikopoulos and W. H. Sandholm. Journal of Economic Theory, vol. 177, pp. 315-364, September 2018.

[J24] - On the convergence of gradient-like flows with noisy gradient input
P. Mertikopoulos and M. Staudigl. SIAM Journal on Optimization, vol. 28, no. 1, pp. 163-197, January 2018.

[C41] - Bandit learning in concave N-person games
M. Bravo, D. S. Leslie, and P. Mertikopoulos. In NeurIPS '18: Proceedings of the 32nd International Conference on Neural Information Processing Systems, 2018.

[C40] - Learning in games with lossy feedback
Z. Zhou, P. Mertikopoulos, S. Athey, N. Bambos, P. W. Glynn, and Y. Ye. In NeurIPS '18: Proceedings of the 32nd International Conference on Neural Information Processing Systems, 2018.

[C39] - On the convergence of stochastic forward-backward-forward algorithms with variance reduction
M. Staudigl, R. I. Bot, P. T. Vuong, and P. Mertikopoulos. In NeurIPS '18: Workshop on Smooth Games, Optimization and Machine Learning (SGO&ML).

[C38] - Power control with random delays: Robust feedback averaging
A. Ward, Z. Zhou, P. Mertikopoulos, and N. Bambos. In CDC '18: Proceedings of the 57th IEEE Annual Conference on Decision and Control, 2018.

[C37] - Distributed asynchronous optimization with unbounded delays: How slow can you go?
Z. Zhou, P. Mertikopoulos, N. Bambos, P. W. Glynn, Y. Ye, J. Li, and F.-F. Li. In ICML '18: Proceedings of the 35th International Conference on Machine Learning, 2018.

[C36] - A resource allocation framework for network slicing
M. Leconte, G. Paschos, P. Mertikopoulos, and U. C. Kozat. In INFOCOM '18: Proceedings of the 37th IEEE International Conference on Computer Communications, 2018.

[C35] - Cycles in adversarial regularized learning
P. Mertikopoulos, C. Papadimitriou, and G. Piliouras. In SODA '18: Proceedings of the 29th annual ACM-SIAM Symposium on Discrete Algorithms, 2018.

[J23] - On the robustness of learning in games with stochastically perturbed payoff observations
M. Bravo and P. Mertikopoulos. Games and Economic Behavior, John Nash Memorial Special Issue, vol. 103, pp. 41-66, May 2017.

[J22] - Distributed stochastic optimization via matrix exponential learning
P. Mertikopoulos, E. V. Belmega, R. Negrel, and L. Sanguinetti. IEEE Transactions on Signal Processing, vol. 65, no. 9, pp. 2277-2290, May 2017.

[J21] - A continuous-time approach to online optimization
J. Kwon and P. Mertikopoulos. Journal of Dynamics and Games, vol. 4, no. 2, pp. 125-148, April 2017.

[J20] - Semi-cognitive radio networks: A novel dynamic spectrum sharing mechanism
A. S. Shafigh, P. Mertikopoulos, S. Glisic, and Y. M. Fang. IEEE Transactions on Cognitive Communications and Networking, vol. 3, no. 1, pp. 97-111, March 2017.

[J19] - Auction-based resource allocation in OpenFlow multi-tenant networks
S. D'Oro, L. Galluccio, P. Mertikopoulos, G. Morabito, and S. Palazzo. Computer Networks, vol. 115, pp. 29-41, March 2017.

[J18] - Mixed-strategy learning with continuous action sets
S. Perkins, P. Mertikopoulos, and D. S. Leslie. IEEE Transactions on Automatic Control, vol. 62, no. 1, pp. 379-384, January 2017.

[C34] - The asymptotic behavior of the price of anarchy
R. Colini-Baldeschi, R. Cominetti, P. Mertikopoulos, and M. Scarsini. In WINE '17: Proceedings of the 13th Conference on Web and Internet Economics, 2017.

[C33] - Countering feedback delays in multi-agent learning
Z. Zhou, P. Mertikopoulos, N. Bambos, P. W. Glynn, and C. Tomlin. In NeurIPS '17: Proceedings of the 31st International Conference on Neural Information Processing Systems, 2017.

[C32] - Stochastic mirror descent in variationally coherent optimization problems
Z. Zhou, P. Mertikopoulos, N. Bambos, S. Boyd, and P. W. Glynn. In NeurIPS '17: Proceedings of the 31st International Conference on Neural Information Processing Systems, 2017.

[C31] - Learning with bandit feedback in potential games
J. Cohen, A. Héliou, and P. Mertikopoulos. In NeurIPS '17: Proceedings of the 31st International Conference on Neural Information Processing Systems, 2017.

[C30] - Least action routing: Identifying the optimal path in a wireless relay network
A. L. Moustakas, P. Mertikopoulos, Z. Zhou, and N. Bambos. In PIMRC '17: Proceedings of the 28th annual IEEE International Symposium on Personal, Indoor and Mobile Radio Communications, 2017.

[C29] - Power control in wireless networks via dual averaging
Z. Zhou, P. Mertikopoulos, A. L. Moustakas, S. Mehdian, N. Bambos and P. W. Glynn. In GLOBECOM '17: Proceedings of the 2017 IEEE Global Telecommunications Conference, 2017.

[C28] - Mirror descent learning in continuous games
Z. Zhou, P. Mertikopoulos, A. L. Moustakas, N. Bambos, and P. W. Glynn. In CDC '17: Proceedings of the 56th IEEE Annual Conference on Decision and Control, 2017.

[C27] - Convergence to Nash equilibrium in continuous games with noisy first-order feedback
P. Mertikopoulos and M. Staudigl. In CDC '17: Proceedings of the 56th IEEE Annual Conference on Decision and Control, 2017.

[C26] - Hedging under uncertainty: regret minimization meets exponentially fast convergence
J. Cohen, A. Héliou, and P. Mertikopoulos. In SAGT '17: Proceedings of the 10th International Symposium on Algorithmic Game Theory, 2017.

[S1] - GameSeer: visualization for game dynamics
Mathematica package for numerical integration and visualization of game dynamics.

[W2] - Boltzmann meets Nash: Energy-efficient routing in optical networks under uncertainty
P. Mertikopoulos, A. L. Moustakas, and A. Tzanakaki. Working paper.

[J17] - Learning in games via reinforcement and regularization
P. Mertikopoulos and W. H. Sandholm. Mathematics of Operations Research, vol. 41, no. 4, pp. 1297–1324, November 2016.

[J16] - Power optimization in random wireless networks
A. L. Moustakas, P. Mertikopoulos, and N. Bambos. IEEE Transactions on Information Theory, vol. 62, no. 9, pp. 5030-5058, September 2016.

[J15] - A stochastic approximation algorithm for stochastic semidefinite programming
B. Gaujal and P. Mertikopoulos. Probability in the Engineering and Informational Sciences, vol. 30, no. 3, pp. 431-454, July 2016.

[J14] - Learning to be green: Robust energy efficiency maximization in dynamic MIMO-OFDM systems
P. Mertikopoulos and E. V. Belmega. IEEE Journal on Selected Areas in Communications, vol. 34, no. 4, pp. 743-757, March 2016.

[J13] - Imitation dynamics with payoff shocks
P. Mertikopoulos and Y. Viossat. International Journal of Game Theory, vol. 45, no. 1, pp. 291–320, March 2016.

[J12] - Learning in an uncertain world: MIMO covariance matrix optimization with imperfect feedback
P. Mertikopoulos and A. L. Moustakas. IEEE Transactions on Signal Processing, vol. 64, no. 1, pp. 5–18, January 2016

[C25] - Interference mitigation via pricing in time-varying cognitive radio systems
A. Marcastel, E. V. Belmega, P. Mertikopoulos, and I. Fijalkow. In NetGCoop '16: Proceedings of the 6th International Conference on Network Games, Control and Optimization, 2016.

[C24] - Distributed learning for resource allocation under uncertainty
P. Mertikopoulos, E. V. Belmega, and L. Sanguinetti. In GlobalSIP '16: Proceedings of the 2016 IEEE Global Conference on Signal and Information Processing, 2016.

[C23] - Online interference mitigation via learning in dynamic IoT environments
A. Marcastel, E. V. Belmega, P. Mertikopoulos, and I. Fijalkow. In GLOBECOM '16: Proceedings of the 2016 IEEE Global Telecommunications Conference, 2016.

[C22] - Online power allocation for opportunistic radio access in dynamic OFDM networks
A. Marcastel, E. V. Belmega, P. Mertikopoulos, and I. Fijalkow. In VTC '16-Fall: Proceedings of the 2016 IEEE Vehicular Technology Conference.

[C21] - A novel dynamic network architecture model based on stochastic geometry and game theory
A. S. Shafigh, P. Mertikopoulos, and S. Glisic. In ICC '16: Proceedings of the 2016 IEEE International Conference on Communications, 2016.

[W1] - Power control via online learning in non-stationary MIMO networks
I. Stiakogiannakis, P. Mertikopoulos, and C. Touati. Working paper.

[J11] - Inertial game dynamics and applications to constrained optimization
R. Laraki and P. Mertikopoulos. SIAM Journal on Control and Optimization, vol. 53, no. 5, pp. 3141–3170, October 2015.

[J10] - Interference-based pricing for opportunistic multi-carrier cognitive radio systems
S. D'Oro, P. Mertikopoulos, A. L. Moustakas, and S. Palazzo. IEEE Transactions on Wireless Communications, vol. 14, no. 12, pp. 6536–6549, December 2015.

[J9] - Energy-aware competitive power allocation for heterogeneous networks under QoS constraints
G. Bacci, E. V. Belmega, P. Mertikopoulos, and L. Sanguinetti. IEEE Transactions on Wireless Communications, vol. 14, no. 9, pp. 4728–4742, September 2015.

[J8] - Penalty-regulated dynamics and robust learning procedures in games
P. Coucheney, B. Gaujal, and P. Mertikopoulos. Mathematics of Operations Research, vol. 40, no. 3, pp. 611-633, August 2015.

[C20] - Cost-efficient power allocation in OFDMA cognitive radio networks
S. D'Oro, P. Mertikopoulos, A. L. Moustakas, and S. Palazzo. In EUCNC '15: Proceedings of the 2015 European Conference on Networks and Communications, 2015.

[C19] - No more tears: A no-regret approach to power control in dynamically varying MIMO networks
I. Stiakogiannakis, P. Mertikopoulos, and C. Touati. In WiOpt '15: Proceedings of the 13th International Symposium and Workshops on Modeling and Optimization in Mobile, Ad Hoc and Wireless Networks, 2015.

[C18] - Energy-efficient power allocation in dynamic multi-carrier systems
E. V. Belmega and P. Mertikopoulos. In VTC '15-Spring: Proceedings of the 2015 IEEE Vehicular Technology Conference.

[J7] - Transmit without regrets: Online optimization in MIMO–OFDM cognitive radio systems
P. Mertikopoulos and E. V. Belmega. IEEE Journal on Selected Areas in Communications, vol. 32, no. 11, pp. 1987–1999, November 2014.

[C17] - No regrets: Distributed power control under time-varying channels and QoS requirements
I. Stiakogiannakis, P. Mertikopoulos, and C. Touati. In Allerton '14: Proceedings of the 51st Annual Allerton Conference on Communication, Control, and Computing, 2014.

[C16] - Distributed optimization in multi-user MIMO systems with imperfect and delayed information
P. Coucheney, B. Gaujal, and P. Mertikopoulos. In ISIT '14: Proceedings of the 2014 IEEE International Symposium on Information Theory, 2014.

[C15] - Adaptive transmit policies for cost-efficient power allocation in multi-carrier systems
S. D'Oro, P. Mertikopoulos, A. L. Moustakas, and S. Palazzo. In WiOpt '14: Proceedings of the 12th International Symposium and Workshops on Modeling and Optimization in Mobile, Ad Hoc and Wireless Networks, 2014.

[C14] - Energy-aware competitive link adaptation in small-cell networks
G. Bacci, E. V. Belmega, P. Mertikopoulos, and L. Sanguinetti. In WiOpt '14: Proceedings of the 12th International Symposium and Workshops on Modeling and Optimization in Mobile, Ad Hoc and Wireless Networks, 2014.

[J6] - Higher-order game dynamics
R. Laraki and P. Mertikopoulos. Journal of Economic Theory, vol. 148, no. 6, pp. 2666–2695, November 2013.

[C13] - Adaptive spectrum management in MIMO-OFDM cognitive radio: An exponential learning approach
P. Mertikopoulos and E. V. Belmega. In ValueTools '13: Proceedings of the 7th International Conference on Performance Evaluation Methodologies and Tools, 2013.

[C12] - Entropy-driven optimization dynamics for Gaussian vector multiple access channels
P. Mertikopoulos and A. L. Moustakas. In ICC '13: Proceedings of the 2013 IEEE International Conference on Communications, 2013.

[C11] - Accelerating population-based search heuristics by adaptive resource allocation
J. Lepping, P. Mertikopoulos, and D. Trystram. In GECCO '13: Proceedings of the 15th ACM Annual Conference on Genetic and Evolutionary Computation, 2013.

[C10] - Riemannian-geometric optimization methods for MIMO multiple access channels
P. Mertikopoulos and A. L. Moustakas. In ISIT '13: Proceedings of the 2013 IEEE International Symposium on Information Theory, 2013.

[J5] - Distributed learning policies for power allocation in multiple access channels
P. Mertikopoulos, E. V. Belmega, A. L. Moustakas, and S. Lasaulce. IEEE Journal on Selected Areas in Communications, vol. 30, pp. 96–106, January 2012.

[C9] - Strange bedfellows: Riemann, Gibbs and vector Gaussian multiple access channels
P. Mertikopoulos. In NetGCoop '12: Proceedings of the 6th International Conference on Network Games, Control and Optimization, 2012.

[C8] - Matrix exponential learning: Distributed optimization in MIMO systems
P. Mertikopoulos, E. V. Belmega, and A. L. Moustakas. In ISIT '12: Proceedings of the 2012 IEEE International Symposium on Information Theory, 2012.

[J4] - Neutral stability, drift, and the diversification of languages
C. Pawlowitsch, P. Mertikopoulos, and N. Ritt. Journal of Theoretical Biology, vol. 287, pp. 1–12, July 2011.

[J3] - Living at the edge: A large deviations approach to the outage MIMO capacity
P. Kazakopoulos, P. Mertikopoulos, A. L. Moustakas, and G. Caire. IEEE Transactions on Information Theory, vol. 57, pp. 1984–2007, April 2011.

[C7] - Selfish Routing Revisited: Degeneracy, Evolution and Stochastic Fluctuations
P. Mertikopoulos, and A. L. Moustakas. In ValueTools '11: Proceedings of the 5th International Conference on Performance Evaluation Methodologies and Tools, 2011.

[C6] - Dynamic power allocation games in parallel multiple access channels
P. Mertikopoulos, E. V. Belmega, A. L. Moustakas, and S. Lasaulce. In ValueTools '11: Proceedings of the 5th International Conference on Performance Evaluation Methodologies and Tools, 2011.

[J2] - The emergence of rational behavior in the presence of stochastic perturbations
P. Mertikopoulos and A. L. Moustakas. Annals of Applied Probability, vol. 20, no. 4, pp. 1359–1388, 2010.

[C5] - Distribution of MIMO mutual information: A large deviations approach
P. Kazakopoulos, P. Mertikopoulos, A. L. Moustakas, G. Caire. In ITW '09: Proceedings of the 2009 IEEE Information Theory Workshop, 2009.

[C4] - Learning in the presence of noise
P. Mertikopoulos and A. L. Moustakas. In GameNets '09: Proceedings of the 1st International Conference on Game Theory for Networks, 2009.

[J1] - Correlated anarchy in overlapping wireless networks
P. Mertikopoulos and A. L. Moustakas. IEEE Journal on Selected Areas in Communications, vol. 26, pp. 1160–1169, September 2008.

[C3] - Vertical handover between wireless standards
N. Dimitriou, P. Mertikopoulos, and A. L. Moustakas. In ICC '08: Proceedings of the 2008 IEEE International Conference on Communications, 2008.

[C2] - Vertical handover between wireless service providers
P. Mertikopoulos, A. L. Moustakas, and N. Dimitriou. In WiOpt '08: Proceedings of the 6th International Symposium on Modeling and Optimization in Mobile, Ad Hoc, and Wireless Networks, 2008.

[C1] - The simplex game: Can selfish users learn to operate efficiently in wireless networks?
P. Mertikopoulos and A. L. Moustakas. In ValueTools '07: Proceedings of the 2nd International Conference on Performance Evaluation Methodologies and Tools, 2007.

Collaborations

Over the years, I’ve been fortunate enough to work with some amazing people. This page is intended as a gateway to the rest of their work (NB: affiliations may be out-of-date):

Nifty tech tag lists from Wouter Beeftink