| First-order methods almost always avoid strict saddle points JD Lee, I Panageas, G Piliouras, M Simchowitz, MI Jordan, B Recht Mathematical programming 176 (1), 311-337, 2019 | 365 | 2019 |
| Cycles in adversarial regularized learning P Mertikopoulos, C Papadimitriou, G Piliouras ACM-SIAM Symposium on Discrete Algorithms (SODA), 2018., 2017 | 359 | 2017 |
| Optimistic mirror descent in saddle-point problems: Going the extra (gradient) mile M Panayotis, B Lecouat, H Zenati, CS Foo, V Chandrasekhar, G Piliouras ICLR, 2019 | 358* | 2019 |
| Multiplicative updates outperform generic no-regret learning in congestion games R Kleinberg, G Piliouras, É Tardos Proceedings of the forty-first annual ACM symposium on Theory of computing …, 2009 | 195 | 2009 |
| Gradient descent converges to minimizers: The case of non-isolated critical points I Panageas, G Piliouras Proceedings of the 2017 ACM Conference on Innovations in Theoretical …, 2016 | 192* | 2016 |
| Multiplicative Weights Update in Zero-Sum Games JP Bailey, G Piliouras Proceedings of the 2018 ACM Conference on Economics and Computation, 321-338, 2018 | 155 | 2018 |
| {\alpha}-Rank: Multi-Agent Evaluation by Evolution S Omidshafiei, C Papadimitriou, G Piliouras, K Tuyls, M Rowland, ... Scientific Reports (9), 2019 | 139 | 2019 |
| Multiplicative Weights Update with Constant Step-Size in Congestion Games: Convergence, Limit Cycles and Chaos G Palaiopanos, I Panageas, G Piliouras 31st Annual Conference on Neural Information Processing Systems, 2017 | 139 | 2017 |
| Global Convergence of Multi-Agent Policy Gradient in Markov Potential Games S Leonardos, W Overman, I Panageas, G Piliouras arXiv preprint arXiv:2106.01969, 2021 | 130 | 2021 |
| Incentives in Ethereum's Hybrid Casper Protocol V Buterin, D Reijsbergen, S Leonardos, G Piliouras IEEE International Conference on Blockchain and Cryptocurrency (ICBC) 2019, 2019 | 124 | 2019 |
| The unusual effectiveness of averaging in GAN training Y Yazici, CS Foo, S Winkler, KH Yap, G Piliouras, V Chandrasekhar arXiv preprint arXiv:1806.04498, 2018 | 98* | 2018 |
| Optimization Despite Chaos: Convex Relaxations to Complex Limit Sets via Poincaré Recurrence G Piliouras, JS Shamma ACM-SIAM Symposium on Discrete Algorithms (SODA 14), 2014 | 95 | 2014 |
| From Poincaré recurrence to convergence in imperfect information games: Finding equilibrium via regularization J Perolat, R Munos, JB Lespiau, S Omidshafiei, M Rowland, P Ortega, ... International Conference on Machine Learning, 8525-8535, 2021 | 85 | 2021 |
| Weighted Voting on the Blockchain: Improving Consensus in Proof of Stake Protocols S Leonardos, D Reijsbergen, G Piliouras IEEE International Conference on Blockchain and Cryptocurrency (ICBC) 2019, 2019 | 84 | 2019 |
| Beyond the Nash equilibrium barrier R Kleinberg, K Ligett, G Piliouras, E Tardos Symposium on Innovations in Computer Science (ICS), 2011 | 80 | 2011 |
| From Nash Equilibria to Chain Recurrent Sets: An Algorithmic Solution Concept for Game Theory C Papadimitriou, G Piliouras Entropy 20 (10), 782, 2018 | 73* | 2018 |
| Risk sensitivity of price of anarchy under uncertainty G Piliouras, E Nikolova, JS Shamma ACM Transactions on Economics and Computation (TEAC) 5 (1), 1-27, 2016 | 72 | 2016 |
| Finite regret and cycles with fixed step-size via alternating gradient descent-ascent JP Bailey, G Gidel, G Piliouras Conference on Learning Theory, 391-407, 2020 | 69 | 2020 |
| Scaling up Mean Field Games with Online Mirror Descent J Perolat, S Perrin, R Elie, M Laurière, G Piliouras, M Geist, K Tuyls, ... arXiv preprint arXiv:2103.00623, 2021 | 67 | 2021 |
| Vortices Instead of Equilibria in MinMax Optimization: Chaos and Butterfly Effects of Online Learning in Zero-Sum Games YK Cheung, G Piliouras COLT 2019, 2019 | 67 | 2019 |
Stefanos LeonardosLecturer in machine learning, King's College London確認したメール アドレス: kcl.ac.uk
