Stop the war!Остановите войну!
for scientists:
Google
Google Scholar
Semantic Scholar
IA Scholar
CiteSeerX
ORCIDGeorgios Piliouras
Person information
Refine list
refinements active!
zoomed in on ?? of ?? records
view refined list in
export refined list as
showing all ?? records
2020 – today
- 2022
[j17]Stefanos Leonardos
, Georgios Piliouras:
Exploration-exploitation in multi-agent learning: Catastrophe theory meets game theory. Artif. Intell. 304: 103653 (2022)- [j16]Georgios Piliouras, Mark Rowland, Shayegan Omidshafiei, Romuald Elie, Daniel Hennes, Jerome T. Connor, Karl Tuyls:
Evolutionary Dynamics and Phi-Regret Minimization in Games. J. Artif. Intell. Res. 74: 1125-1158 (2022) - [j15]Barnabé Monnot, Francisco Benita, Georgios Piliouras:
Routing Games in the Wild: Efficiency, Equilibration, Regret, and a Price of Anarchy Bound via Long Division. ACM Trans. Economics and Comput. 10(1): 2:1-2:26 (2022) - [c77]Aleksander Czechowski, Georgios Piliouras:
Poincaré-Bendixson Limit Sets in Multi-Agent Learning. AAMAS 2022: 318-326 - [c76]Paul Muller, Mark Rowland, Romuald Elie, Georgios Piliouras, Julien Pérolat, Mathieu Laurière, Raphaël Marinier, Olivier Pietquin, Karl Tuyls:
Learning Equilibria in Mean-Field Games: Introducing Mean-Field PSRO. AAMAS 2022: 926-934 - [c75]Julien Pérolat, Sarah Perrin, Romuald Elie, Mathieu Laurière, Georgios Piliouras, Matthieu Geist, Karl Tuyls, Olivier Pietquin:
Scaling Mean Field Games by Online Mirror Descent. AAMAS 2022: 1028-1037 - [c74]Jin Xing Lim, Barnabé Monnot, Georgios Piliouras:
Blockchain-based Mechanism Design for Collaborative Mathematical Research. ICBC 2022: 1-9 - [c73]Yun Kuen Cheung, Georgios Piliouras, Yixin Tao:
The Evolution of Uncertainty of Learning in Games. ICLR 2022 - [c72]Stefanos Leonardos, Will Overman, Ioannis Panageas, Georgios Piliouras:
Global Convergence of Multi-Agent Policy Gradient in Markov Potential Games. ICLR 2022 - [c71]Andjela Mladenovic, Iosif Sakos, Gauthier Gidel, Georgios Piliouras:
Generalized Natural Gradient Flows in Hidden Convex-Concave Games and GANs. ICLR 2022 - [c70]Kimon Antonakopoulos, Panayotis Mertikopoulos, Georgios Piliouras, Xiao Wang:
AdaGrad Avoids Saddle Points. ICML 2022: 731-771 - [c69]Mathieu Laurière, Sarah Perrin, Sertan Girgin, Paul Muller, Ayush Jain, Theophile Cabannes, Georgios Piliouras, Julien Pérolat, Romuald Elie, Olivier Pietquin, Matthieu Geist:
Scalable Deep Reinforcement Learning Algorithms for Mean Field Games. ICML 2022: 12078-12095 - [i75]Georgios Piliouras, Fang-Yi Yu:
Multi-agent Performative Prediction: From Global Stability and Optimality to Chaos. CoRR abs/2201.10483 (2022) - [i74]Jakub Bielawski, Thiparat Chotibut, Fryderyk Falniowski, Michal Misiurewicz, Georgios Piliouras:
Unpredictable dynamics in congestion games: memory loss can prevent chaos. CoRR abs/2201.10992 (2022) - [i73]Gabriel P. Andrade, Rafael M. Frongillo, Georgios Piliouras:
No-Regret Learning in Games is Turing Complete. CoRR abs/2202.11871 (2022) - [i72]Mathieu Laurière, Sarah Perrin, Sertan Girgin, Paul Muller, Ayush Jain, Theophile Cabannes, Georgios Piliouras, Julien Pérolat, Romuald Élie, Olivier Pietquin, Matthieu Geist:
Scalable Deep Reinforcement Learning Algorithms for Mean Field Games. CoRR abs/2203.11973 (2022) - [i71]Jason Milionis, Christos H. Papadimitriou, Georgios Piliouras, Kelly Spendlove:
Nash, Conley, and Computation: Impossibility and Incompleteness in Game Dynamics. CoRR abs/2203.14129 (2022) - [i70]Andre Wibisono, Molei Tao, Georgios Piliouras:
Alternating Mirror Descent for Constrained Min-Max Games. CoRR abs/2206.04160 (2022) - [i69]Georgios Piliouras, Lillian J. Ratliff, Ryann Sim, Stratis Skoulakis:
Fast Convergence of Optimistic Gradient Ascent in Network Zero-Sum Extensive Form Games. CoRR abs/2207.08426 (2022) - 2021
- [c68]Stefanos Leonardos, Georgios Piliouras:
Exploration-Exploitation in Multi-Agent Learning: Catastrophe Theory Meets Game Theory. AAAI 2021: 11263-11271 - [c67]Stratis Skoulakis, Tanner Fiez, Ryann Sim, Georgios Piliouras, Lillian J. Ratliff:
Evolutionary Game Theory Squared: Evolving Agents in Endogenously Evolving Zero-Sum Games. AAAI 2021: 11343-11351 - [c66]Stefanos Leonardos, Barnabé Monnot, Daniël Reijsbergen, Efstratios Skoulakis, Georgios Piliouras:
Dynamical analysis of the EIP-1559 Ethereum fee market. AFT 2021: 114-126 - [c65]Daniël Reijsbergen, Shyam Sridhar, Barnabé Monnot, Stefanos Leonardos, Stratis Skoulakis, Georgios Piliouras:
Transaction Fees on a Honeymoon: Ethereum's EIP-1559 One Month Later. Blockchain 2021: 196-204 - [c64]Jin Xing Lim, Barnabé Monnot, Shaowei Lin, Georgios Piliouras:
A Blockchain-Based Approach for Collaborative Formalization of Mathematics and Programs. Blockchain 2021: 321-326 - [c63]Gabriel P. Andrade, Rafael M. Frongillo, Georgios Piliouras:
Learning in Matrix Games can be Arbitrarily Complex. COLT 2021: 159-185 - [c62]Dimitris Fotakis, Panagiotis Kostopanagiotis, Vasileios Nakos, Georgios Piliouras, Stratis Skoulakis:
On the Approximability of Multistage Min-Sum Set Cover. ICALP 2021: 65:1-65:19 - [c61]Jakub Bielawski, Thiparat Chotibut, Fryderyk Falniowski, Grzegorz Kosiorowski, Michal Misiurewicz, Georgios Piliouras:
Follow-the-Regularized-Leader Routes to Chaos in Routing Games. ICML 2021: 925-935 - [c60]Yun Kuen Cheung, Georgios Piliouras:
Online Optimization in Games via Control Theory: Connecting Regret, Passivity and Poincaré Recurrence. ICML 2021: 1855-1865 - [c59]Dimitris Fotakis, Georgios Piliouras, Stratis Skoulakis:
Efficient Online Learning for Dynamic k-Clustering. ICML 2021: 3396-3406 - [c58]Julien Pérolat, Rémi Munos, Jean-Baptiste Lespiau, Shayegan Omidshafiei, Mark Rowland, Pedro A. Ortega, Neil Burch, Thomas W. Anthony, David Balduzzi, Bart De Vylder, Georgios Piliouras, Marc Lanctot, Karl Tuyls:
From Poincaré Recurrence to Convergence in Imperfect Information Games: Finding Equilibrium via Regularization. ICML 2021: 8525-8535 - [c57]Yun Kuen Cheung, Stefanos Leonardos, Georgios Piliouras:
Learning in Markets: Greed Leads to Chaos but Following the Price is Right. IJCAI 2021: 111-117 - [c56]Emmanouil-Vasileios Vlatakis-Gkaragkounis, Lampros Flokas, Georgios Piliouras:
Solving Min-Max Optimization with Hidden Structure via Gradient Descent Ascent. NeurIPS 2021: 2373-2386 - [c55]Tanner Fiez, Ryann Sim, Stratis Skoulakis, Georgios Piliouras, Lillian J. Ratliff:
Online Learning in Periodic Zero-Sum Games. NeurIPS 2021: 10313-10325 - [c54]Stefanos Leonardos, Georgios Piliouras, Kelly Spendlove:
Exploration-Exploitation in Multi-Agent Competition: Convergence with Bounded Rationality. NeurIPS 2021: 26318-26331 - [i68]Lampros Flokas, Emmanouil-Vasileios Vlatakis-Gkaragkounis, Georgios Piliouras:
Solving Min-Max Optimization with Hidden Structure via Gradient Descent Ascent. CoRR abs/2101.05248 (2021) - [i67]Aleksander Czechowski, Georgios Piliouras:
Poincaré-Bendixson Limit Sets in Multi-Agent Learning. CoRR abs/2102.00053 (2021) - [i66]Jakub Bielawski, Thiparat Chotibut, Fryderyk Falniowski, Grzegorz Kosiorowski, Michal Misiurewicz, Georgios Piliouras:
Follow-the-Regularized-Leader Routes to Chaos in Routing Games. CoRR abs/2102.07974 (2021) - [i65]Stefanos Leonardos, Barnabé Monnot, Daniël Reijsbergen, Stratis Skoulakis, Georgios Piliouras:
Dynamical Analysis of the EIP-1559 Ethereum Fee Market. CoRR abs/2102.10567 (2021) - [i64]Julien Pérolat, Sarah Perrin, Romuald Elie, Mathieu Laurière, Georgios Piliouras, Matthieu Geist, Karl Tuyls, Olivier Pietquin:
Scaling up Mean Field Games with Online Mirror Descent. CoRR abs/2103.00623 (2021) - [i63]Gabriel P. Andrade, Rafael M. Frongillo, Georgios Piliouras:
Learning in Matrix Games can be Arbitrarily Complex. CoRR abs/2103.03405 (2021) - [i62]Yun Kuen Cheung, Stefanos Leonardos, Georgios Piliouras:
Learning in Markets: Greed Leads to Chaos but Following the Price is Right. CoRR abs/2103.08529 (2021) - [i61]Stefanos Leonardos, Will Overman, Ioannis Panageas, Georgios Piliouras:
Global Convergence of Multi-Agent Policy Gradient in Markov Potential Games. CoRR abs/2106.01969 (2021) - [i60]Dimitris Fotakis, Georgios Piliouras, Stratis Skoulakis:
Efficient Online Learning for Dynamic k-Clustering. CoRR abs/2106.04336 (2021) - [i59]Yun Kuen Cheung, Georgios Piliouras:
Online Optimization in Games via Control Theory: Connecting Regret, Passivity and Poincaré Recurrence. CoRR abs/2106.04748 (2021) - [i58]Yun Kuen Cheung, Stefanos Leonardos, Georgios Piliouras, Shyam Sridhar:
From Griefing to Stability in Blockchain Mining Economies. CoRR abs/2106.12332 (2021) - [i57]Stefanos Leonardos, Georgios Piliouras, Kelly Spendlove:
Exploration-Exploitation in Multi-Agent Competition: Convergence with Bounded Rationality. CoRR abs/2106.12928 (2021) - [i56]Georgios Piliouras, Mark Rowland, Shayegan Omidshafiei, Romuald Elie, Daniel Hennes, Jerome T. Connor, Karl Tuyls:
Evolutionary Dynamics and Φ-Regret Minimization in Games. CoRR abs/2106.14668 (2021) - [i55]Dimitris Fotakis, Panagiotis Kostopanagiotis, Vasileios Nakos, Georgios Piliouras, Stratis Skoulakis:
On the Approximability of Multistage Min-Sum Set Cover. CoRR abs/2107.13344 (2021) - [i54]Georgios Piliouras, Xiao Wang:
Constants of Motion: The Antidote to Chaos in Optimization and Game Dynamics. CoRR abs/2109.03974 (2021) - [i53]James P. Bailey, Sai Ganesh Nagarajan, Georgios Piliouras:
Stochastic Multiplicative Weights Updates in Zero-Sum Games. CoRR abs/2110.02134 (2021) - [i52]Daniël Reijsbergen, Shyam Sridhar, Barnabé Monnot, Stefanos Leonardos, Stratis Skoulakis, Georgios Piliouras:
Transaction Fees on a Honeymoon: Ethereum's EIP-1559 One Month Later. CoRR abs/2110.04753 (2021) - [i51]Tanner Fiez, Ryann Sim, Stratis Skoulakis, Georgios Piliouras, Lillian J. Ratliff:
Online Learning in Periodic Zero-Sum Games. CoRR abs/2111.03377 (2021) - [i50]Paul Muller, Mark Rowland, Romuald Elie, Georgios Piliouras, Julien Pérolat, Mathieu Laurière, Raphaël Marinier, Olivier Pietquin, Karl Tuyls:
Learning Equilibria in Mean-Field Games: Introducing Mean-Field PSRO. CoRR abs/2111.08350 (2021) - [i49]Jin Xing Lim, Barnabé Monnot, Shaowei Lin, Georgios Piliouras:
A Blockchain-Based Approach for Collaborative Formalization of Mathematics and Programs. CoRR abs/2111.10824 (2021) - [i48]Georgios Piliouras, Ryann Sim, Stratis Skoulakis:
Optimal No-Regret Learning in General Games: Bounded Regret with Unbounded Step-Sizes via Clairvoyant MWU. CoRR abs/2111.14737 (2021) - 2020
- [j14]Constandina Koki, Stefanos Leonardos, Georgios Piliouras:
Do Cryptocurrency Prices Camouflage Latent Economic Effects? A Bayesian Hidden Markov Approach. Future Internet 12(3): 59 (2020) - [j13]Vitalik Buterin, Daniël Reijsbergen, Stefanos Leonardos, Georgios Piliouras:
Incentives in Ethereum's hybrid Casper protocol. Int. J. Netw. Manag. 30(5) (2020) - [j12]Stefanos Leonardos, Daniël Reijsbergen, Georgios Piliouras:
Weighted voting on the blockchain: Improving consensus in proof of stake protocols. Int. J. Netw. Manag. 30(5) (2020) - [j11]Stefanos Leonardos, Daniël Reijsbergen, Georgios Piliouras:
PREStO: A Systematic Framework for Blockchain Consensus Protocols. IEEE Trans. Engineering Management 67(4): 1028-1044 (2020) - [c53]Sai Ganesh Nagarajan, David Balduzzi, Georgios Piliouras:
Robust Self-organization in Games: Symmetries, Conservation Laws and Dimensionality Reduction. AAMAS 2020: 1946-1948 - [c52]James P. Bailey, Gauthier Gidel, Georgios Piliouras:
Finite Regret and Cycles with Fixed Step-Size via Alternating Gradient Descent-Ascent. COLT 2020: 391-407 - [c51]David Balduzzi, Wojciech M. Czarnecki, Tom Anthony, Ian M. Gemp, Edward Hughes, Joel Z. Leibo, Georgios Piliouras, Thore Graepel:
Smooth markets: A basic mechanism for organizing gradient-based learners. ICLR 2020 - [c50]Sai Ganesh Nagarajan, David Balduzzi, Georgios Piliouras:
From Chaos to Order: Symmetry and Conservation Laws in Game Dynamics. ICML 2020: 7186-7196 - [c49]Yun Kuen Cheung, Georgios Piliouras:
Chaos, Extremism and Optimism: Volume Analysis of Learning in Games. NeurIPS 2020 - [c48]Thiparat Chotibut, Fryderyk Falniowski, Michal Misiurewicz, Georgios Piliouras:
The route to chaos in routing games: When is price of anarchy too optimistic? NeurIPS 2020 - [c47]Dimitris Fotakis, Thanasis Lianeas, Georgios Piliouras, Stratis Skoulakis:
Efficient Online Learning of Optimal Rankings: Dimensionality Reduction via Gradient Descent. NeurIPS 2020 - [c46]Emmanouil-Vasileios Vlatakis-Gkaragkounis, Lampros Flokas, Thanasis Lianeas, Panayotis Mertikopoulos, Georgios Piliouras:
No-Regret Learning and Mixed Nash Equilibria: They Do Not Mix. NeurIPS 2020 - [c45]Francisco Benita, Vittorio Bilò, Barnabé Monnot, Georgios Piliouras, Cosimo Vinci:
Data-Driven Models of Selfish Routing: Why Price of Anarchy Does Depend on Network Topology. WINE 2020: 252-265 - [c44]Stefanos Leonardos, Iosif Sakos, Costas Courcoubetis, Georgios Piliouras:
Catastrophe by Design in Population Games: Destabilizing WastefulLocked-In Technologies. WINE 2020: 473 - [i47]David Balduzzi, Wojciech M. Czarnecki, Thomas W. Anthony, Ian M. Gemp, Edward Hughes, Joel Z. Leibo, Georgios Piliouras, Thore Graepel:
Smooth markets: A basic mechanism for organizing gradient-based learners. CoRR abs/2001.04678 (2020) - [i46]Julien Pérolat, Rémi Munos, Jean-Baptiste Lespiau, Shayegan Omidshafiei, Mark Rowland, Pedro A. Ortega, Neil Burch, Thomas W. Anthony, David Balduzzi, Bart De Vylder, Georgios Piliouras, Marc Lanctot, Karl Tuyls:
From Poincaré Recurrence to Convergence in Imperfect Information Games: Finding Equilibrium via Regularization. CoRR abs/2002.08456 (2020) - [i45]Yun Kuen Cheung, Georgios Piliouras:
Chaos, Extremism and Optimism: Volume Analysis of Learning in Games. CoRR abs/2005.13996 (2020) - [i44]Stefanos Leonardos, Iosif Sakos, Costas Courcoubetis, Georgios Piliouras:
Catastrophe by Design in Population Games: Destabilizing Wasteful Locked-in Technologies. CoRR abs/2007.12877 (2020) - [i43]Francisco Benita, Vittorio Bilò, Barnabé Monnot, Georgios Piliouras, Cosimo Vinci:
Data-Driven Models of Selfish Routing: Why Price of Anarchy Does Depend on Network Topology. CoRR abs/2009.12871 (2020) - [i42]Lampros Flokas, Emmanouil-Vasileios Vlatakis-Gkaragkounis, Thanasis Lianeas, Panayotis Mertikopoulos, Georgios Piliouras:
No-regret learning and mixed Nash equilibria: They do not mix. CoRR abs/2010.09514 (2020) - [i41]Dimitris Fotakis, Thanasis Lianeas, Georgios Piliouras, Stratis Skoulakis:
Efficient Online Learning of Optimal Rankings: Dimensionality Reduction via Gradient Descent. CoRR abs/2011.02817 (2020) - [i40]Stefanos Leonardos, Georgios Piliouras:
Exploration-Exploitation in Multi-Agent Learning: Catastrophe Theory Meets Game Theory. CoRR abs/2012.03083 (2020) - [i39]Stratis Skoulakis, Tanner Fiez, Ryann Sim, Georgios Piliouras, Lillian J. Ratliff:
Evolutionary Game Theory Squared: Evolving Agents in Endogenously Evolving Zero-Sum Games. CoRR abs/2012.08382 (2020)
2010 – 2019
- 2019
- [j10]Jason D. Lee, Ioannis Panageas, Georgios Piliouras, Max Simchowitz, Michael I. Jordan, Benjamin Recht:
First-order methods almost always avoid strict saddle points. Math. Program. 176(1-2): 311-337 (2019) - [c43]James P. Bailey, Georgios Piliouras:
Multi-Agent Learning in Network Zero-Sum Games is a Hamiltonian System. AAMAS 2019: 233-241 - [c42]Yun Kuen Cheung, Georgios Piliouras:
Vortices Instead of Equilibria in MinMax Optimization: Chaos and Butterfly Effects of Online Learning in Zero-Sum Games. COLT 2019: 807-834 - [c41]Vitalik Buterin, Daniël Reijsbergen, Stefanos Leonardos, Georgios Piliouras:
Incentives in Ethereum's Hybrid Casper Protocol. IEEE ICBC 2019: 236-244 - [c40]Stefanos Leonardos, Daniël Reijsbergen, Georgios Piliouras:
Weighted Voting on the Blockchain: Improving Consensus in Proof of Stake Protocols. IEEE ICBC 2019: 376-384 - [c39]Panayotis Mertikopoulos, Bruno Lecouat, Houssam Zenati, Chuan-Sheng Foo, Vijay Chandrasekhar, Georgios Piliouras:
Optimistic mirror descent in saddle-point problems: Going the extra (gradient) mile. ICLR (Poster) 2019 - [c38]Yasin Yazici, Chuan-Sheng Foo, Stefan Winkler, Kim-Hui Yap, Georgios Piliouras, Vijay Chandrasekhar:
The Unusual Effectiveness of Averaging in GAN Training. ICLR (Poster) 2019 - [c37]Ioannis Panageas, Georgios Piliouras, Xiao Wang:
Multiplicative Weights Updates as a distributed constrained optimization algorithm: Convergence to second-order stationary points almost always. ICML 2019: 4961-4969 - [c36]Nikos Leonardos, Stefanos Leonardos, Georgios Piliouras:
Oceanic Games: Centralization Risks and Incentives in Blockchain Mining. MARBLE 2019: 183-199 - [c35]Ioannis Panageas, Georgios Piliouras, Xiao Wang:
First-order methods almost always avoid saddle points: The case of vanishing step-sizes. NeurIPS 2019: 6471-6480 - [c34]Emmanouil-Vasileios Vlatakis-Gkaragkounis, Lampros Flokas, Georgios Piliouras:
Efficiently avoiding saddle points with zero order methods: No gradients required. NeurIPS 2019: 10066-10077 - [c33]Emmanouil-Vasileios Vlatakis-Gkaragkounis, Lampros Flokas, Georgios Piliouras:
Poincaré Recurrence, Cycles and Spurious Equilibria in Gradient-Descent-Ascent for Non-Convex Non-Concave Zero-Sum Games. NeurIPS 2019: 10450-10461 - [c32]Mark Rowland, Shayegan Omidshafiei, Karl Tuyls, Julien Pérolat, Michal Valko, Georgios Piliouras, Rémi Munos:
Multiagent Evaluation under Incomplete Information. NeurIPS 2019: 12270-12282 - [c31]James P. Bailey, Georgios Piliouras:
Fast and Furious Learning in Zero-Sum Games: Vanishing Regret with Non-Vanishing Step Sizes. NeurIPS 2019: 12977-12987 - [c30]Kurtulus Gemici, Elias Koutsoupias, Barnabé Monnot, Christos H. Papadimitriou, Georgios Piliouras:
Wealth Inequality and the Price of Anarchy. STACS 2019: 31:1-31:16 - [c29]Victor Boone, Georgios Piliouras:
From Darwin to Poincaré and von Neumann: Recurrence and Cycles in Evolutionary and Algorithmic Game Theory. WINE 2019: 85-99 - [i38]Yasin Yazici, Bruno Lecouat, Chuan-Sheng Foo, Stefan Winkler, Kim-Hui Yap, Georgios Piliouras, Vijay Chandrasekhar:
Venn GAN: Discovering Commonalities and Particularities of Multiple Distributions. CoRR abs/1902.03444 (2019) - [i37]Francisco Benita, Garvit Bansal, Georgios Piliouras, Bige Tunçer:
Short-distance commuters in the smart city. CoRR abs/1902.08028 (2019) - [i36]Shayegan Omidshafiei, Christos H. Papadimitriou, Georgios Piliouras, Karl Tuyls, Mark Rowland, Jean-Baptiste Lespiau, Wojciech M. Czarnecki, Marc Lanctot, Julien Pérolat, Rémi Munos:
α-Rank: Multi-Agent Evaluation by Evolution. CoRR abs/1903.01373 (2019) - [i35]James P. Bailey, Georgios Piliouras:
Multi-Agent Learning in Network Zero-Sum Games is a Hamiltonian System. CoRR abs/1903.01720 (2019) - [i34]Vitalik Buterin, Daniël Reijsbergen, Stefanos Leonardos, Georgios Piliouras:
Incentives in Ethereum's Hybrid Casper Protocol. CoRR abs/1903.04205 (2019) - [i33]Stefanos Leonardos, Daniël Reijsbergen, Georgios Piliouras:
Weighted Voting on the Blockchain: Improving Consensus in Proof of Stake Protocols. CoRR abs/1903.04213 (2019) - [i32]Nikos Leonardos, Stefanos Leonardos, Georgios Piliouras:
Oceanic Games: Centralization Risks and Incentives in Blockchain Mining. CoRR abs/1904.02368 (2019) - [i31]James P. Bailey, Georgios Piliouras:
Fast and Furious Learning in Zero-Sum Games: Vanishing Regret with Non-Vanishing Step Sizes. CoRR abs/1905.04532 (2019) - [i30]Yun Kuen Cheung, Georgios Piliouras:
Vortices Instead of Equilibria in MinMax Optimization: Chaos and Butterfly Effects of Online Learning in Zero-Sum Games. CoRR abs/1905.08396 (2019) - [i29]Thiparat Chotibut, Fryderyk Falniowski, Michal Misiurewicz, Georgios Piliouras:
The route to chaos in routing games: Population increase drives period-doubling instability, chaos & inefficiency with Price of Anarchy equal to one. CoRR abs/1906.02486 (2019) - [i28]Stefanos Leonardos, Daniël Reijsbergen, Georgios Piliouras:
PREStO: A Systematic Framework for Blockchain Consensus Protocols. CoRR abs/1906.06540 (2019) - [i27]Tushar Vaidya, Thiparat Chotibut, Georgios Piliouras:
Broken Detailed Balance and Non-Equilibrium Dynamics in Noisy Social Learning Models. CoRR abs/1906.11481 (2019) - [i26]James P. Bailey, Gauthier Gidel, Georgios Piliouras:
Finite Regret and Cycles with Fixed Step-Size via Alternating Gradient Descent-Ascent. CoRR abs/1907.04392 (2019) - [i25]Mark Rowland, Shayegan Omidshafiei, Karl Tuyls, Julien Pérolat, Michal Valko, Georgios Piliouras, Rémi Munos:
Multiagent Evaluation under Incomplete Information. CoRR abs/1909.09849 (2019) - [i24]Victor Boone, Georgios Piliouras:
From Darwin to Poincaré and von Neumann: Recurrence and Cycles in Evolutionary and Algorithmic Game Theory. CoRR abs/1910.01334 (2019) - [i23]Lampros Flokas, Emmanouil-Vasileios Vlatakis-Gkaragkounis, Georgios Piliouras:
Poincaré Recurrence, Cycles and Spurious Equilibria in Gradient-Descent-Ascent for Non-Convex Non-Concave Zero-Sum Games. CoRR abs/1910.13010 (2019) - [i22]Lampros Flokas, Emmanouil-Vasileios Vlatakis-Gkaragkounis, Georgios Piliouras:
Efficiently avoiding saddle points with zero order methods: No gradients required. CoRR abs/1910.13021 (2019) - 2018
- [j9]Christos H. Papadimitriou, Georgios Piliouras:
From Nash Equilibria to Chain Recurrent Sets: An Algorithmic Solution Concept for Game Theory. Entropy 20(10): 782 (2018) - [j8]Ger Yang, David Basanta, Georgios Piliouras:
Bifurcation Mechanism Design - From Optimal Flat Taxes to Better Cancer Treatments. Games 9(2): 21 (2018) - [j7]Christos H. Papadimitriou, Georgios Piliouras:
Game dynamics as the meaning of a game. SIGecom Exch. 16(2): 53-63 (2018) - [c28]Sai Ganesh Nagarajan, Sameh Mohamed, Georgios Piliouras:
Three Body Problems in Evolutionary Game Dynamics: Convergence, Periodicity and Limit Cycles. AAMAS 2018: 685-693 - [c27]Tushar Vaidya, Carlos Murguia, Georgios Piliouras:
Learning Agents in Financial Markets: Consensus Dynamics on Volatility. AAMAS 2018: 2106-2108 - [c26]Georgios Piliouras, Leonard J. Schulman:
Learning Dynamics and the Co-Evolution of Competing Sexual Species. ITCS 2018: 59:1-59:3 - [c25]Vincent Chia, Pieter H. Hartel, Qingze Hum, Sebastian Ma, Georgios Piliouras, Daniël Reijsbergen, Mark van Staalduinen, Pawel Szalachowski:
Rethinking Blockchain Security: Position Paper. iThings/GreenCom/CPSCom/SmartData 2018: 1273-1280 - [c24]James P. Bailey, Georgios Piliouras:
Multiplicative Weights Update in Zero-Sum Games. EC 2018: 321-338 - [c23]Panayotis Mertikopoulos, Christos H. Papadimitriou, Georgios Piliouras:
Cycles in Adversarial Regularized Learning. SODA 2018: 2703-2717 - [i21]Kurtulus Gemici, Elias Koutsoupias, Barnabé Monnot, Christos H. Papadimitriou, Georgios Piliouras:
Wealth Inequality and the Price of Anarchy. CoRR abs/1802.09269 (2018) - [i20]Vincent Chia, Pieter H. Hartel, Qingze Hum, Sebastian Ma, Georgios Piliouras, Daniël Reijsbergen, Mark van Staalduinen, Pawel Szalachowski:
Rethinking Blockchain Security: Position Paper. CoRR abs/1806.04358 (2018) - [i19]Yasin Yazici, Chuan Sheng Foo, Stefan Winkler, Kim-Hui Yap, Georgios Piliouras, Vijay Chandrasekhar:
The Unusual Effectiveness of Averaging in GAN Training. CoRR abs/1806.04498 (2018) - [i18]Panayotis Mertikopoulos, Houssam Zenati, Bruno Lecouat, Chuan-Sheng Foo, Vijay Chandrasekhar, Georgios Piliouras:
Mirror descent in saddle-point problems: Going the extra (gradient) mile. CoRR abs/1807.02629 (2018) - 2017
- [j6]Barnabé Monnot, Georgios Piliouras:
Limits and limitations of no-regret learning in games. Knowl. Eng. Rev. 32: e21 (2017) - [c22]Ioannis Panageas, Georgios Piliouras:
Gradient Descent Only Converges to Minimizers: Non-Isolated Critical Points and Invariant Regions. ITCS 2017: 2:1-2:12 - [c21]Ruta Mehta, Ioannis Panageas, Georgios Piliouras, Prasad Tetali, Vijay V. Vazirani:
Mutation, Sexual Reproduction and Survival in Dynamic Environments. ITCS 2017: 16:1-16:29 - [c20]