 |
Research Interests:
|
Biography
I recieved my bachelor diploma in Mathematics from National and Kapodistrian University of Athens, Greece and my master in Optimization and Game Theory in Paris 6 (UPMC) in Paris, France.
Finally, I received my Ph.D. in Adaptive First Order Methods for Convex structured optimization problems from the University of Grenoble-Alpes under the supervision of Prof. P. Mertikopoulos and. Prof. E.V. Belmega.Â
Currently, I am a postdoctoral researcher  at the Laboratory for Information and Inference Systems hosted by Prof. Volkan Cehver.Â
My interests lie at the intersection of Game Theory, Â Convex Optimization and Variational Inequalities.
Publications with LIONS
Universal Gradient Methods for Stochastic Convex Optimization
2024. 41st International Conference on Machine Learning (ICML 2024), Vienna, Austria, 2024-07-21.Improving SAM Requires Rethinking its Optimization Formulation
2024. 41st International Conference on Machine Learning (ICML 2024), Vienna, Austria, July 21-27, 2024.On the Generalization of Stochastic Gradient Descent with Momentum
Journal Of Machine Learning Research. 2024. Vol. 25, p. 1 – 56.Distributed Extra-Gradient With Optimal Complexity And Communication Guarantees
2023. 11th International Conference on Learning Representations (ICLR), Kigali, Rwanda, May 1-5, 2023.ADAGRAD Avoids Saddle Points
2022. 38th International Conference on Machine Learning (ICML), Baltimore, MD, Jul 17-23, 2022. p. 731 – 771.No-regret learning in games with noisy feedback: Faster rates and adaptivity via learning rate separation
2022. 36th Conference on Neural Information Processing Systems (NeurIPS 2022), New Orleans, USA, November 28 – December 9, 2022.UNDERGRAD: A Universal Black-Box Optimization Method with Almost Dimension-Free Convergence Rate Guarantees
2022. 39th International Conference on Machine Learning (ICML), Baltimore, Maryland, USA, July 17-23, 2022.Extra Newton: A First Approach to Noise-Adaptive Accelerated Second-Order Methods
2022. 36th Conference on Neural Information Processing Systems (NeurIPS), New Orleans, Louisianna, USA, November 28-December 9, 2022.Adaptive Stochastic Variance Reduction for Non-convex Finite-Sum Minimization
2022. 36th Conference on Neural Information Processing Systems (NeurIPS), New Orleans, Louisianna, USA, November 28-December 9, 2022.Sifting through the Noise: Universal First-Order Methods for Stochastic Variational Inequalities
2021. NeurIPS 2021 : Thirty-fifth Conference on Neural Information Processing Systems, Sydney, Australia [Virtual only], December 6-14, 2021.Publication prior to EPFL
K. Antonakopoulos and P. Mertikopoulos, âAdaptive First-Order Methods Revisited: Convex Minimization without Lipschitz Requirements,â in NeurIPS 2021: Proceedings of the 35th International Conference on Neural Processing Information Systems, 2021
D.-Q. Vu, K. Antonakopoulos and P. Mertikopoulos, âFast Routing in an Uncertain World: Adaptive Learn- ing in Congestion Games via Exponential Weights,â in NeurIPS 2021: Proceedings of the 35th International Conference on Neural Processing Information Systems, 2021.
Y.-G. Hsieh, K. Antonakopoulos and P. Mertikopoulos,âAdaptive Learning in Continuous Games: Optimal Regret Bounds and Convergence to Equilibrium,â in COLT 2021: Proceedings of 34th Annual Conference on Learning Theory, 2021.
K. Antonakopoulos, E.V. Belmega and P. Mertikopoulos, âAdaptive Extra-Gradient Methods for Min-Max Optimization and Games,â in ICLR 2021: Proceedings of the 9th International Conference on Learning Repre- sentations, 2021.
K. Antonakopoulos, E.V. Belmega and P. Mertikopoulos, âOnline and Stochastic Optimization Beyond Lips- chitz Continuity: A Riemannian Approach,â in ICLR 2020: Proceedings of the 8th International Conference on Learning Representations, 2020.
K. Antonakopoulos, E.V. Belmega and P. Mertikopoulos, âAn Adaptive Mirror-Prox Method for Variational Inequalities with Singular Operators,â in NeurIPS 2019: Proceedings of the 33rd International Conference on Neural Processing Information Systems, 2019.