A continuous-time approach to online optimization J Kwon, P Mertikopoulos Journal of Dynamics and Games 4 (2), 125–148, 2017 | 56 | 2017 |
Unifying mirror descent and dual averaging A Juditsky, J Kwon, É Moulines Mathematical Programming 199 (1), 793-830, 2023 | 27 | 2023 |
Gains and losses are fundamentally different in regret minimization: The sparse case J Kwon, V Perchet Journal of Machine Learning Research 17 (227), 1-32, 2016 | 26 | 2016 |
Sparse Stochastic Bandits J Kwon, V Perchet, C Vernade Proceedings of Machine Learning Research (COLT 2017) 65, 1269–1270, 2017 | 16 | 2017 |
Online Learning and Blackwell Approachability with Partial Monitoring: Optimal Convergence Rates J Kwon, V Perchet Proceedings of Machine Learning Research (AISTATS 2017) 54, 604-613, 2017 | 13 | 2017 |
Refined approachability algorithms and application to regret minimization with global costs J Kwon Journal of Machine Learning Research 22 (200), 1-38, 2021 | 4 | 2021 |
A MOM-based ensemble method for robustness, subsampling and hyperparameter tuning J Kwon, G Lecué, M Lerasle | 3* | 2021 |
Mirror descent strategies for regret minimization and approachability J Kwon Université Pierre-et-Marie-Curie, 2016 | 3 | 2016 |
Blackwell's Approachability with Time-Dependent Outcome Functions and Dot Products. Application to the Big Match J Kwon, B Ziliotto arXiv preprint arXiv:2303.04956, 2023 | 1 | 2023 |
A universal bound on the variations of bounded convex functions J Kwon Journal of Convex Analysis 24 (1), 67--73, 2017 | 1 | 2017 |