| First-order methods almost always avoid saddle points: The case of vanishing step-sizes I Panageas, G Piliouras, X Wang Advances in Neural Information Processing Systems 32, 2019 | 65 | 2019 |
| Last iterate convergence in no-regret learning: constrained min-max optimization for convex-concave landscapes Q Lei, SG Nagarajan, I Panageas International Conference on Artificial Intelligence and Statistics, 1441-1449, 2021 | 50 | 2021 |
| Depth-width trade-offs for relu networks via sharkovsky's theorem V Chatziafratis, SG Nagarajan, I Panageas, X Wang arXiv preprint arXiv:1912.04378, 2019 | 31 | 2019 |
| Fast convergence of langevin dynamics on manifold: Geodesics meet log-sobolev X Wang, Q Lei, I Panageas Advances in Neural Information Processing Systems 33, 18894-18904, 2020 | 23 | 2020 |
| AdaGrad avoids saddle points K Antonakopoulos, P Mertikopoulos, G Piliouras, X Wang International Conference on Machine Learning, 731-771, 2022 | 21 | 2022 |
| Multiplicative weights updates as a distributed constrained optimization algorithm: Convergence to second-order stationary points almost always I Panageas, G Piliouras, X Wang International Conference on Machine Learning, 4961-4969, 2019 | 18 | 2019 |
| On the last-iterate convergence in time-varying zero-sum games: Extra gradient succeeds where optimism fails Y Feng, H Fu, Q Hu, P Li, I Panageas, X Wang Advances in Neural Information Processing Systems 36, 2024 | 6 | 2024 |
| Semi Bandit Dynamics in Congestion Games: Convergence to Nash Equilibrium and No-Regret Guarantees. I Panageas, S Skoulakis, L Viano, X Wang, V Cevher International Conference on Machine Learning, 26904-26930, 2023 | 5 | 2023 |
| Last-iterate Convergence Separation between Extra-gradient and Optimism in Constrained Periodic Games Y Feng, P Li, I Panageas, X Wang arXiv preprint arXiv:2406.10605, 2024 | 2 | 2024 |
| Accelerated multiplicative weights update avoids saddle points almost always Y Feng, I Panageas, X Wang arXiv preprint arXiv:2204.11407, 2022 | 2 | 2022 |
| Prediction Accuracy of Learning in Games: Follow-the-Regularized-Leader meets Heisenberg Y Feng, G Piliouras, X Wang arXiv preprint arXiv:2406.10603, 2024 | | 2024 |
| Riemannian Accelerated Zeroth-order Algorithm: Improved Robustness and Lower Query Complexity C He, Z Pan, X Wang, B Jiang arXiv preprint arXiv:2405.05713, 2024 | | 2024 |
| Convergence to Second-Order Stationarity for Non-negative Matrix Factorization: Provably and Concurrently XW Ioannis Panageas, Stratis Skoulakis, Antonios Varvitsiotis https://arxiv.org/abs/2002.11323, 0 | | |
Ioannis PanageasAssistant Professor, University of California, IrvineEmail verificata su ics.uci.edu
