Publications

For a more up-to-date list see my Google Scholar page. LINK
Multi-agent Performative Prediction: From Global Stability and Optimality to Chaos
with Fang-Yi Yu.
ACM Conference on Economics and Computation (EC), 2022. 		PDF
No-Regret Learning in Games is Turing Complete
with Gabriel P. Andrade and Rafael Frongillo
ACM Conference on Economics and Computation (EC), 2022. 		PDF
Beyond Time-Average Convergence: Near-Optimal Uncoupled Online Learning via Clairvoyant Multiplicative Weights Update
Georgios Piliouras, Ryann Sim and Stratis Skoulakis.
NeurIPS, 2022. 		PDF
Alternating Mirror Descent for Constrained Min-Max Games
with Andre Wibisono and Molei Tao.
NeurIPS, 2022. 		PDF
Matrix Multiplicative Weights Updates in Quantum Zero-Sum Games: Conservation Laws Recurrence
with Rahul Jain and Ryann Sim.
NeurIPS, 2022. 		PDF
Market Equilibria and Risk Diversification in Blockchain Mining Economies
with Yun Kuen (Marco) Cheung, Stefanos Leonardos and Shyam Sridhar.
3rd Conference on Mathematical Research for Blockchain Economy, 2022. 		PDF
From Griefing to Stability in Blockchain Mining Economies
with Yun Kuen (Marco) Cheung, Stefanos Leonardos and Shyam Sridhar.
3rd Conference on Mathematical Research for Blockchain Economy, 2022. 		PDF
AdaGrad Avoids Saddle Points
with Kimon Antonakopoulos, Panayotis Mertikopoulos and Xiao Wang.
ICML, 2022. 		PDF
Scalable Deep Reinforcement Learning Algorithms for Mean Field Games
Mathieu Laurière, Sarah Perrin, Sertan Girgin, Paul Muller, Ayush Jain, Theophile Cabannes, Georgios Piliouras, Julien Pérolat, Romuald Élie, Olivier Pietquin, Matthieu Geist.
ICML, 2022. 		PDF
The Evolution of Uncertainty of Learning in Games
with Yun Kuen Cheung and Yixin Tao.
ICLR, 2022. 		PDF
Global Convergence of Multi-Agent Policy Gradient in Markov Potential Games
with Stefanos Leonardos, Will Overman and Ioannis Panageas.
ICLR, 2022. 		PDF
Generalized Natural Gradient Flows in Hidden Convex-Concave Games and GANs
with Andjela Mladenovic, Iosif Sakos and Gauthier Gidel.
ICLR, 2022. 		PDF
Blockchain-based Mechanism Design for Collaborative Mathematical Research
with Jin Xing Lim and Barnabé Monnot.
IEEE International Conference on Blockchain and Cryptocurrency (ICBC), 2022. 		PDF
Routing Games in the Wild: Efficiency, Equilibration, Regret, and a Price of Anarchy Bound via Long Division
with Barnabé Monnot and Francisco Benita.
ACM Transactions of Economics and Computation, 10 (1), 1-26, 2022. 		PDF
Nash, Conley, and Computation: Impossibility and Incompleteness in Game Dynamics
with Jason Milionis, Christos Papadimitriou and Kelly Spendlove.
International Symposium on Algorithmic Game Theory (SAGT), 2022. 		PDF
Fast Convergence of Optimistic Gradient Ascent in Network Zero-Sum Extensive Form Games
with Lillian Ratliff, Ryann Sim and Stratis Skoulakis.
International Symposium on Algorithmic Game Theory (SAGT), 2022. 		PDF
Exploration-Exploitation in Multi-Agent Learning: Catastrophe Theory Meets Game Theory
with Stefanos Leonardos.
Artificial Intelligence, 2022.
Invited contribution.
 		PDF
Poincaré-Bendixson Limit Sets in Multi-Agent Learning
with Aleksander Czechowski.
Int. Conference on Autonomous Agents and Multiagent Systems (AAMAS), 2022.
Nominated for best paper award.
 		PDF
Learning Equilibria in Mean-Field Games: Introducing Mean-Field PSRO
with Paul Muller, Mark Rowland, Romuald Elie, Julien Perolat, Mathieu Lauriere, Raphael Marinier, Olivier Pietquin, Karl Tuyls.
AAMAS, 2022. 		PDF
Scaling up Mean Field Games with Online Mirror Descent
with Julien Pérolat, Sarah Perrin, Romuald Elie, Mathieu Laurière, Matthieu Geist, Karl Tuyls, Olivier Pietquin.
AAMAS, 2022. 		PDF
Evolutionary Dynamics and Phi-Regret Minimization in Games
with Mark Rowland, Shayegan Omidshafiei, Romuald Elie, Daniel Hennes, Jerome T. Connor and Karl Tuyls.
J. Artif. Intell. Res. 74: 1125-1158, 2022. 		PDF
Exploring the Predictability of Cryptocurrencies via Bayesian Hidden Markov Models
with Constandina Koki and Stefanos Leonardos.
Research in International Business and Finance 59, 2022.
 		PDF
Stochastic Multiplicative Weights Updates in Zero-Sum Games
with James P. Bailey and Sai Ganesh Nagarajan.
Preprint, 2021. 		PDF
Constants of Motion: The Antidote to Chaos in Optimization and Game Dynamics
with Xiao Wang.
Preprint, 2021. 		PDF
A Blockchain-Based Approach for Collaborative Formalization of Mathematics and Programs
with Jin Xing Lim, Barnabé Monnot and Shaowei Lin.
IEEE Blockchain, 2021. 		PDF
Transaction Fees on a Honeymoon: Ethereum's EIP-1559 One Month Later
with Daniël Reijsbergen, Stefanos Leonardos, Shyam Sridhar, Barnabé Monnot and Stratis Skoulakis.
IEEE Blockchain, 2021. 		PDF
Dynamical Analysis of the EIP-1559 Ethereum Fee Market
with Stefanos Leonardos, Barnabé Monnot, Daniël Reijsbergen and Stratis Skoulakis.
ACM Advances in Financial Technologies (AFT), 2021. 		PDF
Exploration-Exploitation in Multi-Agent Competition: Convergence with Bounded Rationality
with Stefanos Leonardos and Kelly Spendlove.
NeurIPS spotlight paper, 2021.
 		PDF
Solving Min-Max Optimization with Hidden Structure via Gradient Descent Ascent
with Emmanouil-Vasileios Vlatakis-Gkaragkounis and Lampros Flokas.
NeurIPS, 2021. 		PDF
Online Learning in Periodic Zero-Sum Games
with Tanner Fiez, Ryann Sim, Stratis Skoulakis, and Lillian Ratliff.
NeurIPS, 2021. 		PDF
Efficient Online Learning for Dynamic k-Clustering
with Dimitris Fotakis and Stratis Skoulakis.
ICML, 2021. 		PDF
Online Optimization in Games via Control Theory: Connecting Regret, Passivity and Poincaré Recurrence
with Yun Kuen (Marco) Cheung.
ICML, 2021. 		PDF
Follow-the-Regularized-Leader Routes to Chaos in Routing Games
with Jakub Bielawski, Thiparat Chotibut and Fryderyk Falniowski, Grzegorz Kosiorowski and Michał Misiurewicz.
ICML, 2021. 		PDF
From Poincaré Recurrence to Convergence in Imperfect Information Games: Finding Equilibrium via Regularization
Julien Perolat, Remi Munos, Jean-Baptiste Lespiau, Shayegan Omidshafiei, Mark Rowland, Pedro Ortega, Neil Burch, Thomas Anthony, David Balduzzi, Bart De Vylder, Georgios Piliouras, Marc Lanctot, Karl Tuyls.
ICML, 2021. 		PDF
PREStO: A Systematic Framework for Blockchain Consensus Protocols
with Stefanos Leonardos and Daniël Reijsbergen.
IEEE Transactions on Engineering Management, 2021.
Best paper award.
 		PDF
Learning in Markets: Greed Leads to Chaos but Following the Price is Right
with Yun Kuen (Marco) Cheung and Stefanos Leonardos.
IJCAI, 2021. 		PDF
On the Approximability of Multistage Min-Sum Set Cover
with Dimitris Fotakis, Panagiotis Kostopanagiotis, Vasileios Nakos and Stratis Skoulakis.
ICALP, 2021. 		PDF
Exploration-Exploitation in Multi-Agent Learning: Catastrophe Theory Meets Game Theory
with Stefanos Leonardos.
AAAI, 2021.
Best paper award.
 		PDF
Evolutionary Game Theory Squared: Evolving Agents in Endogenously Evolving Zero-Sum Games
Stratis Skoulakis, Tanner Fiez, Ryann Sim and Lillian Ratliff.
AAAI, 2021. 		PDF
Broken Detailed Balance and Non-equilibrium Dynamics in a Noisy Social Learning Model
with Tushar Vaidya and Thiparat Chotibut.
Accepted to appear in Physica A: Statistical Mechanics and its Applications, 2021. 		PDF
No-Regret Learning and Mixed Nash Equilibria: They Do Not Mix
with Emmanouil-Vasileios Vlatakis-Gkaragkounis, Thanasis Lianeas, Lampros Flokas and Panayotis Mertikopoulos.
NeurIPS spotlight paper, 2020. 		PDF
Efficient Online Learning of Optimal Rankings: Dimensionality Reduction via Gradient Descent
with Dimitris Fotakis, Thanasis Lianeas and Stratis Skoulakis.
NeurIPS, 2020. 		PDF
The route to chaos in routing games: When is Price of Anarchy too optimistic?
with Thiparat Chotibut and Fryderyk Falniowski and Michał Misiurewicz.
NeurIPS, 2020. 		PDF
Chaos, Extremism and Optimism: Volume Analysis of Learning in Games
with Yun Kuen (Marco) Cheung.
NeurIPS, 2020. 		PDF
Data-Driven Models of Selfish Routing: Why Price of Anarchy Does Depend on Network Topology
with Francisco Benita, Vittorio Bilò, Barnabé Monnot and Cosimo Vinci.
WINE, 2020. 		PDF
Catastrophe by Design in Population Games: Destabilizing Wasteful Locked-in Technologies
with Stefanos Leonardos, Iosif Sakos and Costas Courcoubetis.
WINE, 2020. 		PDF
From Chaos to Order: Symmetry and Conservation Laws in Game Dynamics
with Sai Ganesh Nagarajan and David Balduzzi.
ICML, 2020. 		PDF
Family of Chaotic Maps from Game Theory.
with Thiparat Chotibut and Fryderyk Falniowski and Michał Misiurewicz.
Accepted to appear in Dynamical Systems, 2020. 		PDF
Finite Regret and Cycles with Fixed Step-Size via Alternating Gradient Descent-Ascent
with James P. Bailey and Gauthier Gidel.
COLT, 2020. 		PDF
Smooth Markets: A Basic Mechanism for Organizing Gradient-Based Learners
David Balduzzi, Wojciech M. Czarnecki, Edward Hughes, Joel Leibo, Ian Gemp, Tom Anthony, Georgios Piliouras, Thore Graepel.
ICLR, 2020.
 		PDF
Robust Self-organization in Games: Symmetries, Conservation Laws and Dimensionality Reduction
with Sai Ganesh Nagarajan and David Balduzzi.
Int. Conference on Autonomous Agents and Multiagent Systems (AAMAS), 2020. 		PDF
Location, location, usage: How different notions of centrality can predict land usage in Singapore
with Francisco Benita.
Physica A: Statistical Mechanics and its Applications, 2020. 		PDF
From Darwin to Poincaré and von Neumann: Recurrence and Cycles in Evolutionary and Algorithmic Game Theory
with Victor Boone.
WINE, 2019. 		PDF
Multiagent Evaluation under Incomplete Information
with Mark Rowland, Shayegan Omidshafiei, Karl Tuyls, Julien Perolat, Michal Valko and Remi Munos.
NeurIPS spotlight paper, 2019. 		PDF
Poincaré Recurrence, Cycles and Spurious Equilibria in Gradient-Descent-Ascent for Non-Convex Non-Concave Zero-Sum Games
with Emmanouil-Vasileios Vlatakis-Gkaragkounis and Lampros Flokas.
NeurIPS spotlight paper, 2019. 		PDF
Efficiently avoiding saddle points with zero order methods: No gradients required
with Emmanouil-Vasileios Vlatakis-Gkaragkounis and Lampros Flokas.
NeurIPS, 2019. 		PDF
First-order methods almost always avoid saddle points: The case of vanishing step-sizes
with Ioannis Panageas and Xiao Wang.
NeurIPS, 2019. 		PDF
Fast and Furious Learning in Zero-Sum Games:
Vanishing Regret with Non-Vanishing Step Sizes
with James P. Bailey.
NeurIPS, 2019. 		PDF
Vortices Instead of Equilibria in MinMax Optimization:
Chaos and Butterfly Effects of Online Learning in Zero-Sum Games.
with Yun Kuen (Marco) Cheung.
COLT, 2019. 		PDF
Multiplicative Weights Updates as a distributed constrained optimization algorithm: Convergence to second-order stationary points almost always
with Ioannis Panageas and Xiao Wang.
ICML, 2019. 		PDF
α-Rank: Multi-Agent Evaluation by Evolution.
Shayegan Omidshafiei, Christos Papadimitriou, Georgios Piliouras, Karl Tuyls, Mark Rowland, Jean-Baptiste Lespiau, Wojciech M. Czarnecki, Marc Lanctot, Julien Perolat, Remi Munos.
Scientific Reports, 2019.
Announcement from DeepMind's Twitter feed. Another one.
PDF
Multi-agent Learning in Network Zero-Sum Games is a Hamiltonian System.
with James P. Bailey.
Int. Conference on Autonomous Agents and Multiagent Systems (AAMAS), 2019.
Nominated for best paper award.
 		PDF
Oceanic Games: Centralization Risks and Incentives in Blockchain Mining
with Nikos Leonardos and Stefanos Leonardos.
International Conference on Mathematical Research for Blockchain Economy (MARBLE), 2019.
Best paper award.
News coverage.
PDF
First Order Methods Almost Always Avoid Strict Saddle Points.
with Jason Lee, Ioannis Panageas, Max Simchowitz, Michael Jordan and Benjamin Recht.
Mathematical Programming, issue on non-convex optimization for statistical learning, 2019.
Nice blog article with the key ideas of the proof.
 		PDF
Incentives in Ethereum's Hybrid Casper Protocol.
with Vitalik Buterin, Daniel Reijsbergen and Stefanos Leonardos.
IEEE - International Conference on Blockchain and Cryptocurrency (ICBC), 2019.
Nice medium article with overview of the paper.
 PDF
Weighted Voting on the Blockchain: Improving Consensus in Proof of Stake Protocols.
with Stefanos Leonardos and Daniel Reijsbergen.
IEEE - International Conference on Blockchain and Cryptocurrency (ICBC), 2019.
Best paper award.
 		PDF
Optimistic mirror descent in saddle-point problems: Going the extra (gradient) mile
with Panayotis Mertikopoulos, Houssam Zenati, Bruno Lecouat, Chuan-Sheng Foo and Vijay Chandrasekhar.
International Conference on Learning Representations (ICLR), 2019. 		PDF
The Unusual Effectiveness of Averaging in GAN Training.
with Yasin Yaz, Chuan-Sheng Foo, Stefan Winkler, Kim-Hui Yap and Vijay Chandrasekhar.
International Conference on Learning Representations (ICLR), 2019. 		PDF
Wealth Inequality and the Price of Anarchy
with Kurtuluş Gemici, Elias Koutsoupias, Barnabé Monnot and Christos Papadimitriou.
Symposium on Theoretical Aspects of Computer Science (STACS), 2019. 		PDF
From Nash Equilibria to Chain Recurrent Sets: An Algorithmic Solution Concept for Game Theory
with Christos Papadimitriou.
Entropy 20.10 (2018): 782. 		PDF
Game Dynamics as the Meaning a Game.
with Christos Papadimitriou.
Sigecom Exchanges, 16(2), 2018. 		PDF
Rethinking Blockchain Security: Position Paper.
with Vincent Chia, Pieter H. Hartel, Qingze Hum, Sebastian Ma, Daniel Reijsbergen, Mark van Staalduinen and Pawel Szalachowski.
IEEE Blockchain, 2018. 		PDF
Multiplicative Weight Update in Zero-Sum Games.
with James P. Bailey.
ACM Conference on Economics and Computation (EC), 2018. 		PDF
Three Body Problems in Evolutionary Game Dynamics: Convergence, Periodicity and Limit Cycles
with Sai Ganesh Nagarajan and Sameh Mohamed.
Int. Conference on Autonomous Agents and Multiagent Systems (AAMAS), 2018. (full paper) 		PDF
Learning Dynamics and the Co-evolution of Competing Sexual Species
with Leonard Schulman.
Innovations in Theoretical Computer Science (ITCS), 2018. 		PDF
Cycles in Adversarial Regularized Learning
with Panayotis Mertikopoulos and Christos Papadimitriou
ACM-SIAM Symposium on Discrete Algorithms (SODA), 2018. 		PDF
Learning Agents in Black-Scholes Financial Markets: Consensus Dynamics and Volatility Smiles
with Tushar Vaidya and Carlos Murguia.
International Conference on Autonomous Agents and Multiagent Systems (AAMAS), 2018. 		PDF
Routing Games in the Wild: Efficiency, Equilibration and Regret (Large-Scale Field Experiments in Singapore)
with Barnabé Monnot and Francisco Benita.
Conference on Web and Internet Economics (WINE), 2017. 		PDF
Multiplicative Weights Update with Constant Step-Size in Congestion Games: Convergence, Limit Cycles and Chaos
with Gerasimos Palaiopanos and Ioannis Panageas.
NIPS spotlight paper, 2017. 		PDF
Bifurcation Mechanism Design: From Optimal Flat Taxes to Improved Cancer Treatments
with Ger Yang and David Basanta.
ACM Conference on Economics and Computation (EC), 2017. 		PDF
Gradient Descent Only Converges to Minimizers: Non-Isolated Critical Points and Invariant Regions
with Ioannis Panageas.
Innovations in Theoretical Computer Science (ITCS), 2017. 		PDF
Modeling and analysis of modular structure in diverse biological networks
with Bader Al-Anzi, Sherif Gerges, Noah Olsman, Christopher Ormerod, John Ormerod, Kai Zinn.
Journal of Theoretical Biology 422(7), pages 18-30, 2017. 		PDF
Approximating Nash Equilibria in Tree Polymatrix Games
with Siddharth Barman and Katrina Ligett.
In journal submission, 2017. 		PDF
Mutation, Sexual Reproduction and Survival in Dynamic Environments
with Ruta Mehta, Ioannis Panageas, Prasad Tetali and Vijay V. Vazirani.
Innovations in Theoretical Computer Science (ITCS), 2017. 		PDF
The Computational Complexity of Genetic Diversity
with Ruta Mehta, Ioannis Panageas and Sadra Yazdanbod.
European Symposium on Algorithms (ESA), 2016. 		PDF
Average Case Performance of Replicator Dynamics in Potential Games via Computing Regions of Attraction
with Ioannis Panageas.
ACM Conference on Economics and Computation (EC), 2016. 		PDF
Risk Sensitivity of Price of Anarchy under Uncertainty
Georgios Piliouras, Evdokia Nikolova and Jeff S. Shamma.
ACM Transactions of Economics and Computation 5(1), 2016. 		PDF
Limits and Limitations of No-Regret Learning in Games
with Barnabé Monnot.
International Conference on Autonomous Agents and Multiagent Systems (AAMAS), Adaptive Learning Agents (ALA) Workshop, 2016. Invited to Appear in The Knowledge Engineering Review, Cambridge Univ. Press, 2017. 		PDF
From Nash equilibria to chain recurrent sets: Solution concepts and topology
with Christos Papadimitriou.
Innovations in Theoretical Computer Science (ITCS), 2016. Invited to Entropy Journal Special Issue on "Information Theory in Game Theory". 		PDF
Inferring Activities and Optimal Trips: Lessons from Singapore's National Science Experiment
Barnabé Monnot, Erik Wilhelm, Georgios Piliouras, Yuren Zhou, Daniel Dahlmeier, Hai Yun Lu, Wang Jin.
Complex Systems Design & Management Asia, Advances in Intelligent Systems and Computing Vol. 426, pp 247-264, 2016. 		PDF
Approximating Nash Equilibria in Tree Polymatrix Games
with Siddharth Barman and Katrina Ligett.
International Symposium on Algorithmic Game Theory (SAGT), 2015. 		PDF
Natural Selection as an Inhibitor of Genetic Diversity: Multiplicative Weights Updates Algorithm and a Conjecture of Haploid Genetics
with Ruta Mehta, and Ioannis Panageas.
Innovations in Theoretical Computer Science (ITCS), 2015. 		PDF
LP-based Covering Games with Low Price of Anarchy
with Tomas Valla and Laszlo A. Vegh.
Theory of Computing Systems, October 2014, pages 1-23. 		PDF
Near optimality in covering games by exposing global information
with Nina Balcan, Sara Krehbiel and Jinwoo Shin.
ACM Transactions of Economics and Computation, Volume 2 Issue 4, October 2014. 		PDF
Persistent Patterns: Multi-Agent Learning beyond Equilibrium and Utility
with Henrik Christensen, Carlos Nieto-Granda, and Jeff S. Shamma.
International Conference on Autonomous Agents and Multiagent Systems (AAMAS), 2014. 		PDF
Optimization Despite Chaos: Convex Relaxations to Complex Limit Sets via Poincaré Recurrence
with Jeff S. Shamma.
ACM-SIAM Symposium on Discrete Algorithms (SODA), 2014. 		PDF
Risk Sensitivity of Price of Anarchy under Uncertainty
Georgios Piliouras, Evdokia Nikolova and Jeff S. Shamma.
ACM Conference on Electronic Commerce (EC), 2013. 		PDF
LP-based Covering Games with Low Price of Anarchy
with Tomas Valla and Laszlo A. Vegh.
Workshop on Internet & Network Economics (WINE), 2012. 		PDF
Near optimality in covering and packing games by exposing global information
with Nina Balcan, Sara Krehbiel and Jinwoo Shin.
IEEE Conference on Decision and Control (CDC), 2012. 		PDF
Medium and long-run properties of linguistic community evolution
with Michael J. Fox and Jeff S. Shamma.
International Conference on the Evolution of Language (Evolang IX), 2012. 		PDF
Game Couplings: Learning Dynamics and Applications
with Nina Balcan, Florin Constantin and Jeff S. Shamma.
IEEE Conference on Decision and Control and European Control Conference (CDC-ECC), 2011. 		PDF
Beating the best Nash without regret
with Katrina Ligett.
SIGecom Exchanges 10, 2011.
PDF
Beyond the Nash equilibrium barrier
with Bobby Kleinberg, Katrina Ligett and Éva Tardos.
Symposium on Innovations in Computer Science (ICS), 2011. 		PDF
Coalition formation and price of anarchy in Cournot oligopolies
with Nicole Immorlica and Vangelis Markakis.
Workshop on Internet & Network Economics (WINE), 2010. 		PDF
No regret learning in oligopolies: Cournot vs Bertrand
with Uri Nadav.
International Symposium on Algorithmic Game Theory (SAGT), 2010. 		PDF
Load balancing without regret in the billboard model
with Bobby Kleinberg and Éva Tardos.
Invited to the Special Issue of the Principles of Distributed Computing vol. 24, 2011.
Symposium on Principles of Distributed Computing (PODC), 2009. 		PDF
Multiplicative updates outperform generic no-regret learning in congestion games
with Bobby Kleinberg and Éva Tardos.
ACM Symposium on Theory of Computing (STOC), 2009. 		PDF