Accéder directement au contenu

Panayotis Mertikopoulos

135
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

Image document

A unified stochastic approximation framework for learning in games

Panayotis Mertikopoulos , Ya-Ping Hsieh , Volkan Cevher
Mathematical Programming, 2023, pp.1-40. ⟨10.1007/s10107-023-02001-y⟩
Article dans une revue hal-03874012v2
Image document

Multi-agent online learning in time-varying games

Benoît Duvocelle , Panayotis Mertikopoulos , Mathias Staudigl , Dries Vermeulen
Mathematics of Operations Research, 2023, 48 (2), pp.914-941. ⟨10.1287/moor.2022.1283⟩
Article dans une revue hal-01891545v1
Image document

Learning in nonatomic games, Part I: Finite action spaces and population games

Saeed Hadikhanloo , Rida Laraki , Panayotis Mertikopoulos , Sylvain Sorin
Journal of Dynamics and Games, 2022, 9 (4), pp.433-460. ⟨10.3934/jdg.2022018⟩
Article dans une revue hal-03342992v1
Image document

Distributed stochastic optimization with large delays

Zhengyuan Zhou , Panayotis Mertikopoulos , Nicholas Bambos , Peter W Glynn , Yinyu Ye
Mathematics of Operations Research, 2022, 47 (3), pp.2082-2111. ⟨10.1287/moor.2021.1200⟩
Article dans une revue hal-03342384v1
Image document

Multi-agent online optimization with delays: Asynchronicity, adaptivity, and optimism

Yu-Guan Hsieh , Franck Iutzeler , Jérôme Malick , Panayotis Mertikopoulos
Journal of Machine Learning Research, 2022, 23 (78), pp.1--49
Article dans une revue hal-03410422v1
Image document

Survival of dominated strategies under imitation dynamics

Panayotis Mertikopoulos , Yannick Viossat
Journal of Dynamics and Games, 2022, 9 (4), pp.499-528. ⟨10.3934/jdg.2022021⟩
Article dans une revue hal-03873966v1
Image document

Online Reconfiguration of IoT Applications in the Fog: The Information-Coordination Trade-off

Bruno Donassolo , Arnaud Legrand , Panayotis Mertikopoulos , Ilhem Fajjari
IEEE Transactions on Parallel and Distributed Systems, 2022, 33 (5), pp.1156-1172. ⟨10.1109/TPDS.2021.3097281⟩
Article dans une revue hal-02636987v2
Image document

Robust power management via learning and game design

Zhengyuan Zhou , Panayotis Mertikopoulos , Aris L. Moustakas , Nicholas Bambos , Peter W. Glynn
Operations Research, 2021, 69 (1), pp.331-345. ⟨10.1287/opre.2020.1996⟩
Article dans une revue hal-01643340v1
Image document

Minibatch forward-backward-forward methods for solving stochastic variational inequalities

Radu Ioan Bot , Panayotis Mertikopoulos , Mathias Staudigl , Phan Tu Vuong
Stochastic Systems, 2021, 11 (2), pp.112-139. ⟨10.1287/stsy.2019.0064⟩
Article dans une revue hal-02405776v2
Image document

On the convergence of mirror descent beyond stochastic convex programming

Zhengyuan Zhou , Panayotis Mertikopoulos , Nicholas Bambos , Stephen Boyd , Peter W. Glynn
SIAM Journal on Optimization, 2020, 30 (1), pp.687-716. ⟨10.1137/17M1134925⟩
Article dans une revue hal-01643346v1
Image document

Fast Optimization with Zeroth-Order Feedback in Distributed, Multi-User MIMO Systems

Olivier Bilenne , Panayotis Mertikopoulos , Elena Veronica Belmega
IEEE Transactions on Signal Processing, 2020, 68, pp.6085-6100. ⟨10.1109/TSP.2020.3029983⟩
Article dans une revue hal-02861460v2
Image document

When is selfish routing bad? The price of anarchy in light and heavy traffic

Riccardo Colini-Baldeschi , Roberto Cominetti , Panayotis Mertikopoulos , Marco Scarsini
Operations Research, 2020, 68 (2), pp.411-434. ⟨10.1287/opre.2019.1894⟩
Article dans une revue hal-01891558v1
Image document

Hessian barrier algorithms for linearly constrained optimization problems

Immanuel M Bomze , Panayotis Mertikopoulos , Werner Schachinger , Mathias Staudigl
SIAM Journal on Optimization, 2019, 29, pp.2100 - 2127. ⟨10.1137/18M1215682⟩
Article dans une revue hal-02403531v1
Image document

Online Power Optimization in Feedback-Limited, Dynamic and Unpredictable IoT Networks

Alexandre Marcastel , Elena-Veronica Belmega , Panayotis Mertikopoulos , Inbar Fijalkow
IEEE Transactions on Signal Processing, 2019, 67 (11), pp.2987 - 3000. ⟨10.1109/TSP.2019.2910479⟩
Article dans une revue hal-02189523v1
Image document

Learning in games with continuous action spaces and unknown payoff functions

Panayotis Mertikopoulos , Zhengyuan Zhou
Mathematical Programming, Series A, 2019, 173 (1-2), pp.465-507. ⟨10.1007/s10107-018-1254-8⟩
Article dans une revue hal-01382282v1
Image document

Riemannian game dynamics

Panayotis Mertikopoulos , William H. Sandholm
Journal of Economic Theory, 2018, 177, pp.315-364. ⟨10.1016/j.jet.2018.06.002⟩
Article dans une revue hal-01382281v1
Image document

On the convergence of gradient-like flows with noisy gradient input

Panayotis Mertikopoulos , Mathias Staudigl
SIAM Journal on Optimization, 2018, 28 (1), pp.163-197
Article dans une revue hal-01404586v1
Image document

Stochastic mirror descent dynamics and their convergence in monotone variational inequalities

Panayotis Mertikopoulos , Mathias Staudigl
Journal of Optimization Theory and Applications, 2018, 179 (3), pp.838-867. ⟨10.1007/s10957-018-1346-x⟩
Article dans une revue hal-01643343v1

Mixed-strategy learning with continuous action sets

Steven Perkins , Panayotis Mertikopoulos , David Stuart Leslie
IEEE Transactions on Automatic Control, 2017, 62 (1), pp.379 - 384. ⟨10.1109/TAC.2015.2511930⟩
Article dans une revue hal-01382280v1
Image document

On the robustness of learning in games with stochastically perturbed payoff observations

Mario Bravo , Panayotis Mertikopoulos
Games and Economic Behavior, 2017, 103 (John Nash Memorial Special Issue), pp.41-66. ⟨10.1016/j.geb.2016.06.004⟩
Article dans une revue hal-01098494v1

Auction-based resource allocation in OpenFlow multi-tenant networks

Salvatore d'Oro , Laura Galluccio , Panayotis Mertikopoulos , Giacomo Morabito , Sergio Palazzo
Computer Networks, 2017, 115, pp.29-41
Article dans une revue hal-01643348v1

Semi-cognitive radio networks: A novel dynamic spectrum sharing mechanism

Alireza Shams Shafigh , Panayotis Mertikopoulos , Savo Glisic , Yuguang Michael Fang
IEEE Transactions on Cognitive Communications and Networking, 2017, 3 (1), pp.97-111. ⟨10.1109/TCCN.2017.2681081⟩
Article dans une revue hal-01643344v1
Image document

Distributed stochastic optimization via matrix exponential learning

Panayotis Mertikopoulos , Elena Veronica Belmega , Romain Negrel , Luca Sanguinetti
IEEE Transactions on Signal Processing, 2017, 65 (9), pp.2277-2290. ⟨10.1109/tsp.2017.2656847⟩
Article dans une revue hal-01382285v1

Learning in an uncertain world: MIMO covariance matrix optimization with imperfect feedback

Panayotis Mertikopoulos , Aris L. Moustakas
IEEE Transactions on Signal Processing, 2016, 64 (1), pp.5-18. ⟨10.1109/tsp.2015.2477053⟩
Article dans une revue hal-01382278v1
Image document

Imitation dynamics with payoff shocks

Panayotis Mertikopoulos , Yannick Viossat
International Journal of Game Theory, 2016, 45 (1-2), pp.291-320. ⟨10.1007/s00182-015-0505-7⟩
Article dans une revue hal-01099014v1

Power Optimization in Random Wireless Networks

Aris L. Moustakas , Panayotis Mertikopoulos , Nicholas Bambos
IEEE Transactions on Information Theory, 2016, 62 (9), pp.5030-5058
Article dans une revue hal-01382277v1

Learning to be green: Robust energy efficiency maximization in dynamic MIMO-OFDM systems

Panayotis Mertikopoulos , Elena Veronica Belmega
IEEE Journal on Selected Areas in Communications, 2016, 34 (4), pp.743 - 757
Article dans une revue hal-01382276v1

A stochastic approximation algorithm for stochastic semidefinite programming

Bruno Gaujal , Panayotis Mertikopoulos
Probability in the Engineering and Informational Sciences, 2016, 30 (3 sup), pp.431-454. ⟨10.1017/S0269964816000127⟩
Article dans une revue hal-01382288v1
Image document

Learning in games via reinforcement learning and regularization

Panayotis Mertikopoulos , William H. Sandholm
Mathematics of Operations Research, 2016, 41 (4), pp.1297-1324. ⟨10.1287/moor.2016.0778⟩
Article dans une revue hal-01073491v1

Energy-aware competitive power allocation for heterogeneous networks under QoS constraints

Giacomo Bacci , E. Veronica Belmega , Panayotis Mertikopoulos , Luca Sanguinetti
IEEE Transactions on Wireless Communications, 2015, 14 (9), pp.4728-4742. ⟨10.1109/twc.2015.2425397⟩
Article dans une revue hal-01382296v1
Image document

Inertial Game Dynamics and Applications to Constrained Optimization

Rida Laraki , Panayotis Mertikopoulos
SIAM Journal on Control and Optimization, 2015, 53 (5), ⟨10.1137/130920253⟩
Article dans une revue hal-01483807v1

Interference-based pricing for opportunistic multi-carrier cognitive radio systems

Salvatore d'Oro , Panayotis Mertikopoulos , Aris L. Moustakas , Sergio Palazzo
IEEE Transactions on Wireless Communications, 2015, 14 (12), pp.6536-6549
Article dans une revue hal-01382291v1
Image document

Penalty-Regulated Dynamics and Robust Learning Procedures in Games

Pierre Coucheney , Bruno Gaujal , Panayotis Mertikopoulos
Mathematics of Operations Research, 2015, 40 (3), pp.611-633. ⟨10.1287/moor.2014.0687⟩
Article dans une revue hal-01235243v1
Image document

Transmit without regrets: online optimization in MIMO-OFDM cognitive radio systems

Panayotis Mertikopoulos , E. Veronica Belmega
IEEE Journal on Selected Areas in Communications, 2014, 32 (11), pp.1987-1999
Article dans une revue hal-01073500v1

Higher Order Game Dynamics

Rida Laraki , Panayotis Mertikopoulos
Journal of Economic Theory, 2013, 148 (6), pp.2666-2695
Article dans une revue hal-01382303v1

Distributed learning policies for power allocation in multiple access channels

Panayotis Mertikopoulos , Elena Veronica Belmega , Aris Moustakas , Samson Lasaulce
IEEE Journal on Selected Areas in Communications, 2012, 30 (1), pp 1-11
Article dans une revue hal-00648840v1
Image document

Neutral stability, drift, and the diversification of languages

Christina Pawlowitsch , Panayotis Mertikopoulos , Nikolaus Ritt
Journal of Theoretical Biology, 2011, 287, pp.1. ⟨10.1016/j.jtbi.2011.07.005⟩
Article dans une revue hal-00730286v1

Living at the edge: a large deviations approach to the outage MIMO capacity

Pavlos Kazakopoulos , Panayotis Mertikopoulos , Aris L. Moustakas , Giuseppe Caire
IEEE Transactions on Information Theory, 2011, 57 (4), pp.1984-2007. ⟨10.1109/TIT.2011.2112050⟩
Article dans une revue hal-00788778v1

The Emergence of Rational Behavior in the Presence of Stochastic Perturbations

Panayotis Mertikopoulos , Aris L. Moustakas
The Annals of Applied Probability, 2010, 20 (4), pp.1359-1388. ⟨10.1214/09-AAP651⟩
Article dans une revue hal-01382306v1

Correlated Anarchy in Overlapping Wireless Networks

Panayotis Mertikopoulos , Aris L. Moustakas
IEEE Journal on Selected Areas in Communications, 2008, 26 (7), pp.1160-1169
Article dans une revue hal-01382311v1
Image document

A quadratic speedup in finding Nash equilibria of quantum zero-sum games

Francisca Vasconcelos , Emmanouil-Vasileios Vlatakis-Gkaragkounis , Panayotis Mertikopoulos , Georgios Piliouras , Michael I Jordan
QTML 2023 - Annual international conference on Quantum Techniques in Machine Learning, Nov 2023, CERN, Switzerland. pp.1-54
Communication dans un congrès hal-04312987v1
Image document

Payoff-based learning with matrix multiplicative weights in quantum games

Kyriakos Lotidis , Panayotis Mertikopoulos , Nicholas Bambos , Jose Blanchet
NeurIPS 2023 - 37th Conference on Neural Information Processing Systems, Dec 2023, New Orleans (LA), United States. pp.1-39
Communication dans un congrès hal-04307824v1
Image document

The stability of matrix multiplicative weights dynamics in quantum games

Kyriakos Lotidis , Panayotis Mertikopoulos , Nicholas Bambos
CDC 2023 - 62nd IEEE Conference on Decision and Control, Dec 2023, Singapore, Singapore. pp.1-8
Communication dans un congrès hal-04307803v1
Image document

Riemannian stochastic optimization methods avoid strict saddle points

Ya-Ping Hsieh , Mohammad Reza Karimi , Andreas Krause , Panayotis Mertikopoulos
NeurIPS 2023 - 37th Conference on Neural Information Processing Systems, Dec 2023, New Orleans (LA), United States. pp.1-27
Communication dans un congrès hal-04307876v1
Image document

Exploiting hidden structures in non-convex games for convergence to Nash equilibrium

Iosif Sakos , Emmanouil-Vasileios Vlatakis-Gkaragkounis , Panayotis Mertikopoulos , Georgios Piliouras
NeurIPS 2023 - 37th Conference on Neural Information Processing Systems, Dec 2023, New Orleans (LA), United States. pp.1-32
Communication dans un congrès hal-04312981v1
Image document

The equivalence of dynamic and strategic stability under regularized learning in games

Victor Boone , Panayotis Mertikopoulos
NeurIPS 2023 - 37th Conference on Neural Information Processing Systems, Dec 2023, New Orleans (LA), United States. pp.1-31
Communication dans un congrès hal-04307883v1
Image document

AdaGrad avoids saddle points

Kimon Antonakopoulos , Panayotis Mertikopoulos , Georgios Piliouras , Xiao Wang
ICML 2022 - 39th International Conference on Machine Learning, Jul 2022, Baltimore, United States. pp.1-41
Communication dans un congrès hal-03874036v1
Image document

Nested bandits

Matthieu Martin , Panayotis Mertikopoulos , Thibaud Rahier , Houssam Zenati
ICML 2022 - 39th International Conference on Machine Learning, Jul 2022, Baltimore, United States
Communication dans un congrès hal-03874048v1
Image document

No-Regret Learning in Games with Noisy Feedback: Faster Rates and Adaptivity via Learning Rate Separation

Yu-Guan Hsieh , Kimon Antonakopoulos , Volkan Cevher , Panayotis Mertikopoulos
NeurIPS 2022 - 36th International Conference on Neural Information Processing Systems, Nov 2022, New Orleans, United States
Communication dans un congrès hal-03694134v1
Image document

The dynamics of Riemannian Robbins-Monro algorithms

Mohammad Reza Karimi , Ya-Ping Hsieh , Panayotis Mertikopoulos , Andreas Krause
COLT 2022 - 35th Annual Conference on Learning Theory, Jul 2022, London, United Kingdom. pp.1-31
Communication dans un congrès hal-03874052v1
Image document

Learning in games with quantized payoff observations

Kyriakos Lotidis , Panayotis Mertikopoulos , Nicholas Bambos
CDC 2022 - 61st IEEE Annual Conference on Decision and Control, Dec 2022, Cancun, Mexico. pp.1-8
Communication dans un congrès hal-03874022v1
Image document

UnderGrad: A universal black-box optimization method with almost dimension-free convergence rate guarantees

Kimon Antonakopoulos , Dong Quan Vu , Vokan Cevher , Kfir Yehuda Levy , Panayotis Mertikopoulos
ICML 2022 - 39th International Conference on Machine Learning, Jul 2022, Baltimore, United States. pp.1-31
Communication dans un congrès hal-03874041v1
Image document

Online convex optimization in wireless networks and beyond: The feedback -performance trade-off

Elena Veronica Belmega , Panayotis Mertikopoulos , Romain Negrel
RAWNET 2022 - International Workshop on Resource Allocation and Cooperation in Wireless Networks, Sep 2022, Turin, Italy. pp.1-8
Communication dans un congrès hal-03737125v2
Image document

On the convergence of policy gradient methods to Nash equilibria in general stochastic games

Angeliki Giannou , Kyriakos Lotidis , Panayotis Mertikopoulos , Emmanouil-Vasileios Vlatakis-Gkaragkounis
NeurIPS 2022 - 36th International Conference on Neural Information Processing Systems, Nov 2022, New Orleans, United States. pp.1-43
Communication dans un congrès hal-03874018v1

Asymptotic Degradation of Linear Regression Estimates with Strategic Data Sources

Benjamin Roussillon , Nicolas Gast , Patrick Loiseau , Panayotis Mertikopoulos
ALT 2022 - 33rd International Conference on Algorithmic Learning Theory, Mar 2022, Paris, France. pp.1-31
Communication dans un congrès hal-03593516v1

Online learning in multi-agent systems: Regret, equilibrium, and the road ahead

Panayotis Mertikopoulos
23ème congrès annuel de la Société Française de Recherche Opérationnelle et d'Aide à la Décision, INSA Lyon, Feb 2022, Villeurbanne - Lyon, France
Communication dans un congrès hal-03595344v1
Image document

Pick your neighbor: Local Gauss-Southwell rule for fast asynchronous decentralized optimization

Marina Costantini , Nikolaos Liakopoulos , Panayotis Mertikopoulos , Thrasyvoulos Spyropoulos
CDC 2022 - 61st IEEE Annual Conference on Decision and Control, Dec 2022, Cancun, Mexico
Communication dans un congrès hal-03790278v1
Image document

Adaptive extra-gradient methods for min-max optimization and games

Kimon Antonakopoulos , Veronica E Belmega , Panayotis Mertikopoulos
ICLR 2021 - 9th International Conference on Learning Representations, May 2021, Virtual, Unknown Region. pp.1-28
Communication dans un congrès hal-03342601v1
Image document

Regret minimization in stochastic non-convex learning via a proximal-gradient approach

Nadav Hallak , Panayotis Mertikopoulos , Volkan Cevher
ICML 2021 - 38th International Conference on Machine Learning, Jul 2021, Vienna, Austria
Communication dans un congrès hal-03043872v1
Image document

The last-iterate convergence rate of optimistic mirror descent in stochastic variational inequalities

Waïss Azizian , Franck Iutzeler , Jérôme Malick , Panayotis Mertikopoulos
COLT 2021 - 34th Annual Conference on Learning Theory, Aug 2021, Boulder, United States. pp.1-32
Communication dans un congrès hal-03342583v1
Image document

Zeroth-order non-convex learning via hierarchical dual averaging

Amélie Héliou , Matthieu Martin , Thibaud Rahier , Panayotis Mertikopoulos
ICML 2021 - 38th International Conference on Machine Learning, Jul 2021, Vienna, Austria. pp.1-34
Communication dans un congrès hal-03341912v1
Image document

Equilibrium tracking and convergence in dynamic games

Panayotis Mertikopoulos , Mathias Staudigl
CDC 2021 - 60th IEEE Annual Conference on Decision and Control, Dec 2021, Austin, United States. pp.1-8
Communication dans un congrès hal-03342397v1
Image document

Sifting through the noise: Universal first-order methods for stochastic variational inequalities

Kimon Antonakopoulos , Thomas Pethick , Ali Kavis , Panayotis Mertikopoulos , Volkan Cevher
NeurIPS 2021 - 35th International Conference on Neural Information Processing Systems, Dec 2021, Virtual, Unknown Region. pp.1-39
Communication dans un congrès hal-03357714v1
Image document

Adaptive learning in continuous games: Optimal regret bounds and convergence to Nash equilibrium

Yu-Guan Hsieh , Kimon Antonakopoulos , Panayotis Mertikopoulos
COLT 2021 - the 34th Annual Conference on Learning Theory, Aug 2021, Boulder, United States. pp.1-34
Communication dans un congrès hal-03342410v1
Image document

Survival of the strictest: Stable and unstable equilibria under regularized learning with partial information

Angeliki Giannou , Emmanouil Vasileios Vlatakis-Gkaragkounis , Panayotis Mertikopoulos
COLT 2021 - 34th Annual Conference on Learning Theory, Aug 2021, Boulder, United States. pp.1-30
Communication dans un congrès hal-03342404v1
Image document

Fast routing under uncertainty: Adaptive learning in congestion games with exponential weights

Dong Quan Vu , Kimon Antonakopoulos , Panayotis Mertikopoulos
NeurIPS 2021 - 35th International Conference on Neural Information Processing Systems, Dec 2021, Virtual, Unknown Region. pp.1-36
Communication dans un congrès hal-03357716v1
Image document

Adaptive first-order methods revisited: Convex optimization without Lipschitz requirements

Kimon Antonakopoulos , Panayotis Mertikopoulos
NeurIPS 2021 - 35th International Conference on Neural Information Processing Systems, Dec 2021, Virtual, Unknown Region
Communication dans un congrès hal-03342998v1
Image document

The convergence rate of regularized learning in games: From bandits and uncertainty to optimism and beyond

Angeliki Giannou , Emmanouil Vasileios Vlatakis-Gkaragkounis , Panayotis Mertikopoulos
NeurIPS 2021 - 35th International Conference on Neural Information Processing Systems, Dec 2021, Virtual, Unknown Region. pp.1-28
Communication dans un congrès hal-03357715v1
Image document

Optimization in open networks via dual averaging

Yu-Guan Hsieh , Franck Iutzeler , Jérôme Malick , Panayotis Mertikopoulos
CDC 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
Image document

The limits of min-max optimization algorithms: Convergence to spurious non-critical sets

Ya-Ping Hsieh , Panayotis Mertikopoulos , Volkan Cevher
ICML 2021 - 38th International Conference on Machine Learning, Jul 2021, Vienna, Austria
Communication dans un congrès hal-03043862v1
Image document

Online non-convex optimization with imperfect feedback

Amélie Héliou , Matthieu Martin , Panayotis Mertikopoulos , Thibaud Rahier
NeurIPS 2020 - 34th International Conference on Neural Information Processing Systems, 2020, Vancouver, Canada
Communication dans un congrès hal-03043746v1
Image document

Quick or cheap? Breaking points in dynamic markets

Panayotis Mertikopoulos , Heinrich Nax , Bary Pradelski
EC 2020 - 21st ACM Conference on Economics and Computation, Jul 2020, Budapest, Hungary. pp.1-32
Communication dans un congrès hal-03043688v1
Image document

Derivative-Free Optimization over Multi-User MIMO Networks

Olivier Bilenne , Panayotis Mertikopoulos , Elena Veronica Belmega
NetGCoop '20: The 2020 International Conference on Network Games, Control and Optimization, 2020, Cargese, France
Communication dans un congrès hal-02881559v1
Image document

No-regret learning and mixed Nash equilibria: They do not mix

Lampros Flokas , Emmanouil Vasileios Vlatakis-Gkaragkounis , Thanasis Lianeas , Panayotis Mertikopoulos , Georgios Piliouras
NeurIPS 2020 - 34th International Conference on Neural Information Processing Systems, Dec 2020, Vancouver, Canada. pp.1-24
Communication dans un congrès hal-03043763v1
Image document

Explore Aggressively, Update Conservatively: Stochastic Extragradient Methods with Variable Stepsize Scaling

Yu-Guan Hsieh , Franck Iutzeler , Jérôme Malick , Panayotis Mertikopoulos
NeurIPS '20 - 34th International Conference on Neural Information Processing Systems, Dec 2020, Vancouver / Virtual, Canada. pp.16223--16234
Communication dans un congrès hal-03002844v1
Image document

Online and Stochastic Optimization beyond Lipschitz Continuity: A Riemannian Approach

Kimon Antonakopoulos , Elena Veronica Belmega , Panayotis Mertikopoulos
ICLR 2020 - International Conference on Learning Representations, Apr 2020, Addis Ababa, Ethiopia. pp.1-20
Communication dans un congrès hal-03043671v1
Image document

Gradient-free Online Learning in Games with Delayed Rewards

Amélie Héliou , Panayotis Mertikopoulos , Zhengyuan Zhou
ICML 2020 - 37th International Conference on Machine Learning, Jul 2020, Vienna, Austria. pp.1-11
Communication dans un congrès hal-03043703v1
Image document

Finite-time last-iterate convergence for multi-agent learning in games

Tianyi Lin , Zhengyuan Zhou , Panayotis Mertikopoulos , Michael I Jordan
ICML 2020 - 37th International Conference on Machine Learning, Jul 2020, Vienna, Austria. pp.1-11
Communication dans un congrès hal-03043711v1
Image document

On the almost sure convergence of stochastic gradient descent in non-convex problems

Panayotis Mertikopoulos , Nadav Hallak , Ali Kavis , Volkan Cevher
NeurIPS 2020 - 34th International Conference on Neural Information Processing Systems, Dec 2020, Vancouver, Canada. pp.1-32
Communication dans un congrès hal-03043771v1
Image document

A new regret analysis for Adam-type algorithms

Ahmet Alacaoglu , Yura Malitsky , Panayotis Mertikopoulos , Volkan Cevher
ICML 2020 - 37th International Conference on Machine Learning, Jul 2020, Vienna, Austria. pp.1-10
Communication dans un congrès hal-03043697v1
Image document

Load Aware Provisioning of IoT Services on Fog Computing Platform

Bruno Donassolo , Ilhem Fajjari , Arnaud Legrand , Panayotis Mertikopoulos
IEEE International Conference on Communications (ICC), May 2019, Shanghai, China. ⟨10.1109/ICC.2019.8762052⟩
Communication dans un congrès hal-02056743v1
Image document

Optimistic Mirror Descent in Saddle-Point Problems: Going the Extra (Gradient) Mile

Panayotis Mertikopoulos , Bruno Lecouat , Houssam Zenati , Chuan-Sheng Foo , Vijay Chandrasekhar
ICLR 2019 - 7th International Conference on Learning Representations, May 2019, New Orleans, United States. pp.1-23
Communication dans un congrès hal-02111937v2
Image document

Fog Based Framework for IoT Service Provisioning

Bruno Donassolo , Ilhem Fajjari , Arnaud Legrand , Panayotis Mertikopoulos
CCNC 2019 - IEEE Consumer Communications & Networking Conference, Jan 2019, Las Vegas, United States. pp.1-6, ⟨10.1109/CCNC.2019.8651835⟩
Communication dans un congrès hal-01859695v1
Image document

Gradient-free Online Resource Allocation Algorithms for Dynamic Wireless Networks

Alexandre Marcastel , Elena-Veronica Belmega , Panayotis Mertikopoulos , Inbar Fijalkow
SPAWC 2019 - 20th IEEE International Workshop on Signal Processing Advances in Wireless Communications, Jul 2019, Cannes, France. pp.1-4, ⟨10.1109/SPAWC.2019.8815409⟩
Communication dans un congrès hal-02189108v1
Image document

On the Convergence of Single-Call Stochastic Extra-Gradient Methods

Yu-Guan Hsieh , Franck Iutzeler , Jérôme Malick , Panayotis Mertikopoulos
Advances in Neural Information Processing Systems, Dec 2019, Vancouver, Canada
Communication dans un congrès hal-02403555v1
Image document

An adaptive mirror-prox algorithm for variational inequalities with singular operators

Kimon Antonakopoulos , Elena Veronica Belmega , Panayotis Mertikopoulos
NeurIPS 2019, 2019, Vancouver, Canada
Communication dans un congrès hal-02403562v1
Image document

Convergent Noisy forward-backward-forward algorithms in non-monotone variational inequalities

Mathias Staudigl , Panayotis Mertikopoulos
LSS 2019 - 15th IFAC Symposium on Large Scale Complex Systems: Theory and Applications, May 2019, Delft, Netherlands. pp.120-125, ⟨10.1016/j.ifacol.2019.06.021⟩
Communication dans un congrès hal-02405750v1
Image document

On the convergence of stochastic forward-backward-forward algorithms with variance reduction in pseudo-monotone variational inequalities

Radu Bot , Panayotis Mertikopoulos , Mathias Staudigl , Phan Tu Vuong
NIPS 2018 - Workshop on Smooth Games, Optimization and Machine Learning, Dec 2018, Montréal, Canada. pp.1-5
Communication dans un congrès hal-01949361v1
Image document

Cycles in adversarial regularized learning

Panayotis Mertikopoulos , Christos Harilaos Papadimitriou , Georgios Piliouras
SODA '18 - Twenty-Ninth Annual ACM-SIAM Symposium on Discrete Algorithms, Jan 2018, New Orleans, United States. pp.2703-2717
Communication dans un congrès hal-01643338v1
Image document

Learning in Games with Lossy Feedback

Zhengyuan Zhou , Panayotis Mertikopoulos , Susan Athey , Nicholas Bambos , Peter Glynn
NIPS 2018 - Thirty-second Conference on Neural Information Processing Systems, Dec 2018, Montreal, Canada. pp.1-11
Communication dans un congrès hal-01904461v1
Image document

Distributed Asynchronous Optimization with Unbounded Delays: How Slow Can You Go?

Zhengyuan Zhou , Panayotis Mertikopoulos , Nicholas Bambos , Peter W. Glynn , Yinyu Ye
ICML 2018 - 35th International Conference on Machine Learning, Jul 2018, Stockholm, Sweden. pp.1-10
Communication dans un congrès hal-01891449v1
Image document

Power Control with Random Delays: Robust Feedback Averaging

Andrew Ward , Zhengyuan Zhou , Panayotis Mertikopoulos , Nicholas Bambos
CDC 2018 - 57th IEEE Conference on Decision and Control, Dec 2018, Miami Beach, United States. pp.1-6
Communication dans un congrès hal-01891528v1
Image document

Bandit learning in concave N-person games

Mario Bravo , David Stuart Leslie , Panayotis Mertikopoulos
NIPS 2018 - Thirty-second Conference on Neural Information Processing Systems, Dec 2018, Montréal, Canada. pp.1-24
Communication dans un congrès hal-01891523v1
Image document

A resource allocation framework for network slicing

Mathieu Leconte , Georgios Paschos , Panayotis Mertikopoulos , Ulas Kozat
INFOCOM 2018 - IEEE International Conference on Computer Communications, Apr 2018, Honolulu, United States. pp.1-9
Communication dans un congrès hal-01643349v1

Convergence to Nash equilibrium in continuous games with noisy first-order feedback

Panayotis Mertikopoulos , Mathias Staudigl
CDC '17: Proceedings of the 55th IEEE Annual Conference on Decision and Control, Dec 2017, Melbourne, Australia
Communication dans un congrès hal-01643347v1

Stochastic mirror descent for variationally coherent optimization problems

Zhengyuan Zhou , Panayotis Mertikopoulos , Nicholas Bambos , Stephen Boyd , Peter W. Glynn
NIPS '17: Proceedings of the 31st International Conference on Neural Information Processing Systems, Dec 2017, Long Beach, CA, United States
Communication dans un congrès hal-01643342v1

Hedging under uncertainty: regret minimization meets exponentially fast convergence

Johanne Cohen , Amélie Héliou , Panayotis Mertikopoulos
Symposium on Algorithmic Game Theory (SAGT) 2017, Sep 2017, L'Aquila, Italy. ⟨10.1007/978-3-319-66700-3_20⟩
Communication dans un congrès hal-01382290v1

Power control in wireless networks via dual averaging

Zhengyuan Zhou , Panayotis Mertikopoulos , Aris L. Moustakas , Saied Mehdian , Nicholas Bambos
GLOBECOM '17: Proceedings of the 2017 IEEE Global Telecommunications Conference, Dec 2017, Singapore, Singapore
Communication dans un congrès hal-01643339v1

Least action routing: Identifying the optimal path in a wireless relay network

Aris L. Moustakas , Panayotis Mertikopoulos , Zhengyuan Zhou , Nicholas Bambos
PIMRC'17: 28th annual IEEE International Symposium on Personal, Indoor and Mobile Radio Communications, 2017, Montreal, Canada
Communication dans un congrès hal-01643351v1

Mirror descent learning in continuous games

Zhengyuan Zhou , Panayotis Mertikopoulos , Aris L. Moustakas , Nicholas Bambos , Peter W. Glynn
CDC '17: Proceedings of the 56th IEEE Annual Conference on Decision and Control, Dec 2017, Melbourne, Australia
Communication dans un congrès hal-01643341v1

The asymptotic behavior of the price of anarchy

Riccardo Colini-Baldeschi , Roberto Cominetti , Panayotis Mertikopoulos , Marco Scarsini
WINE 2017: Proceedings of the 13th Conference on Web and Internet Economics, Dec 2017, Bangalore, India
Communication dans un congrès hal-01643345v1

Countering feedback delays in multi-agent learning

Zhengyuan Zhou , Panayotis Mertikopoulos , Nicholas Bambos , Peter W. Glynn , Claire Tomlin
NIPS '17: Proceedings of the 31st International Conference on Neural Information Processing Systems, Dec 2017, Long Beach, CA, United States
Communication dans un congrès hal-01643350v1

Learning with bandit feedback in potential games

Johanne Cohen , Amélie Héliou , Panayotis Mertikopoulos
NIPS '17: Proceedings of the 31st International Conference on Neural Information Processing Systems, Dec 2017, Long Beach, CA, United States
Communication dans un congrès hal-01643352v1

A novel dynamic network architecture model based on stochastic geometry and game theory

Alireza Shams Shafigh , Panayotis Mertikopoulos , Savo Glisic
ICC '16: Proceedings of the 2016 IEEE International Conference on Communications, 2016, Unknown, Unknown Region
Communication dans un congrès hal-01382274v1
Image document

Online Power Allocation for Opportunistic Radio Access in Dynamic OFDM Networks

Alexandre Marcastel , E Veronica Belmega , Panayotis Mertikopoulos , Inbar Fijalkow
2016 IEEE 84th Vehicular Technology Conference (VTC2016-Fall), Sep 2016, Montreal, Canada
Communication dans un congrès hal-01387044v1
Image document

Online Interference Mitigation via Learning in Dynamic IoT Environments

Alexandre Marcastel , E Veronica Belmega , Panayotis Mertikopoulos , Inbar Fijalkow
IEEE WORKSHOP GLOBECOM 2016, Dec 2016, Washington, DC, United States
Communication dans un congrès hal-01387046v1
Image document

Distributed learning for resource allocation under uncertainty

Panayotis Mertikopoulos , Elena Veronica Belmega , Luca Sanguinetti
GlobalSIP 2016 - IEEE Global Conference on Signal and Information Processing, Dec 2016, Washington, United States. ⟨10.1109/globalsip.2016.7905899⟩
Communication dans un congrès hal-01382284v1

Cost-efficient power allocation in OFDMA cognitive radio networks

Salvatore d'Oro , Panayotis Mertikopoulos , Aris L. Moustakas , Sergio Palazzo
EUCNC' 15: Proceedings of the 2015 European Conference on Networks and Communications, 2015, Unknown, Unknown Region
Communication dans un congrès hal-01382292v1

No more tears: A no-regret approach to power control in dynamically varying MIMO networks

Ioannis Stiakogiannakis , Panayotis Mertikopoulos , Corinne Touati
WiOpt '15: Proceedings of the 13th International Symposium and Workshops on Modeling and Optimization in Mobile, Ad Hoc, and Wireless Networks, 2015, Unknown, Unknown Region
Communication dans un congrès hal-01382294v1

Energy-efficient power allocation in dynamic multi-carrier systems

E. Veronica Belmega , Panayotis Mertikopoulos
VTC Spring 2015: Proceedings of the 2015 IEEE Vehicular Technology Conference, 2015, Glasgow, Scotland, Unknown Region
Communication dans un congrès hal-01382293v1
Image document

Energy-Aware Competitive Link Adaptation in Small-Cell Networks

Giacomo Bacci , Veronica Belmega , Panayotis Mertikopoulos , Luca Sanguinetti
12th International Symposium on Modeling and Optimization in Mobile, Ad Hoc, and Wireless Networks (WiOpt), May 2014, Hammamet, Tunisia. ⟨10.1109/wiopt.2014.6850272⟩
Communication dans un congrès hal-01098846v1

Adaptive transmit policies for cost-efficient power allocation in multi-carrier systems

Salvatore d'Oro , Panayotis Mertikopoulos , Aris L. Moustakas , Sergio Palazzo
WiOpt '14: Proceedings of the 12th International Symposium and Workshops on Modeling and Optimization in Mobile, Ad Hoc, and Wireless Networks, 2014, Unknown, Unknown Region
Communication dans un congrès hal-01382298v1

No regrets: Distributed power control under time-varying channels and QoS requirements

Ioannis Stiakogiannakis , Panayotis Mertikopoulos , Corinne Touati
Allerton '14: Proceedings of the 51st Annual Allerton Conference on Communication, Control, and Computing, 2014, Unknown, Unknown Region
Communication dans un congrès hal-01382300v1

Distributed Optimization in Multi-User MIMO Systems with Imperfect and Delayed Information

Pierre Coucheney , Bruno Gaujal , Panayotis Mertikopoulos
ISIT '14: Proceedings of the 2014 IEEE International Symposium on Information Theory, 2014, Unknown, Unknown Region
Communication dans un congrès hal-01382297v1

Adaptive Spectrum Management in MIMO-OFDM Cognitive Radio: An Exponential Learning Approach

Panayotis Mertikopoulos , E. Veronica Belmega
ValueTools '13: Proceedings of the 7th International Conference on Performance Evaluation Methodologies and Tools, 2013, Unknown, Unknown Region
Communication dans un congrès hal-01382305v1

Riemannian-Geometric Optimization Methods for MIMO Multiple Access Channels

Panayotis Mertikopoulos , Aris L. Moustakas
ISIT '13: Proceedings of the 2013 IEEE International Symposium on Information Theory, 2013, Unknown, Unknown Region
Communication dans un congrès hal-01382304v1

Entropy-Driven Optimization Dynamics for Gaussian Vector Multiple Access Channels

Panayotis Mertikopoulos , Aris L. Moustakas
ICC '13: Proceedings of the 2013 IEEE International Conference on Communications, 2013, Unknown, Unknown Region
Communication dans un congrès hal-01382301v1

Accelerating Population-Based Search Heuristics by Adaptive Resource Allocation

Joachim Lepping , Panayotis Mertikopoulos , Denis Trystram
GECCO '13: Proceedings of the 15th ACM Annual Conference on Genetic and Evolutionary Computation, 2013, Unknown, Unknown Region. pp.1165-1172
Communication dans un congrès hal-01382302v1

Matrix Exponential Learning: Distributed Optimization in MIMO systems

Panayotis Mertikopoulos , Elena Veronica Belmega , Aris Moustakas
IEEE International Symposium on Information Theory (ISIT), Jul 2012, United States. pp.3028 -- 3032
Communication dans un congrès hal-00741823v1

Strange bedfellows: Riemann, Gibbs and vector Gaussian multiple access channels

Panayotis Mertikopoulos
NetGCoop'12: Proceedings of the 6th International Conference on Network Games, Control and Optimization, 2012, Unknown
Communication dans un congrès hal-00788010v1

Selfish routing revisited: degeneracy, evolution and stochastic fluctuations

Panayotis Mertikopoulos , Aris L. Moustakas
ValueTools '11: ACM Proceedings of the 5th International Conference on Performance Evaluation Methodologies and Tools, 2011, Cargèse, France. pp.217-226
Communication dans un congrès hal-00788801v1

Dynamic power allocation games in parallel multiple access channels

Panayotis Mertikopoulos , Elena V. Belmega , Aris L. Moustakas , Samson Lasaulce
ValueTools'11: ACM Proceedings of the 5th International Conference on Performance Evaluation Methodologies and Tools, May 2011, Cachan, France. pp.332-341
Communication dans un congrès hal-00788802v1

Distribution of MIMO Mutual Information: a Large Deviations Approach

Pavlos Kazakopoulos , Panayotis Mertikopoulos , Aris L. Moustakas , Giuseppe Caire
ITW '09: Proceedings of the 2009 IEEE workshop on networking and information theory, 2009, Unknown, Unknown Region
Communication dans un congrès hal-01382308v1

Learning in the Presence of Noise

Panayotis Mertikopoulos , Aris L. Moustakas
GameNets '09: Proceedings of the 1st International Conference on Game Theory for Networks, 2009, Unknown, Unknown Region
Communication dans un congrès hal-01382307v1

Vertical Handover Between Wireless Service Providers

Panayotis Mertikopoulos , Aris L. Moustakas , Nikos Dimitriou
WiOpt '08: Proceedings of the 6th International Symposium on Modeling and Optimization in Mobile, Ad Hoc, and Wireless Networks, 2008, Unknown, Unknown Region
Communication dans un congrès hal-01382309v1

Vertical Handover Between Wireless Standards

Nikos Dimitriou , Panayotis Mertikopoulos , Aris L. Moustakas
ICC '08: Proceedings of the 2008 IEEE International Conference on Communications, 2008, Unknown, Unknown Region
Communication dans un congrès hal-01382310v1

The Simplex Game: Can Selfish Users Learn to Operate Efficiently in Wireless Networks?

Panayotis Mertikopoulos , Aris L. Moustakas
ValueTools '07: Proceedings of the 2nd International Conference on Performance Evaluation Methodologies and Tools, 2007, Unknown, Unknown Region
Communication dans un congrès hal-01382312v1