Efstratios (Stratis) Skoulakis

Research Interests:

  • Online Learning
  • Online Algorithms
  • Convex Optimization

 

Biography

Stratis is a postdoctoral research fellow at the Laboratory for Information and Inference Systems hosted by Prof. Volkan Cehver. His interests lie at the intersection of Game Theory, Optimization and Machine Learning.

Stratis received his Ph.D. in Algorithmic Game Theory from the National Technical University of Athens under the supervision of Prof. Dimitris Fotakis. From 2019-2021 he was a postdoctoral research fellow at Singapore University of Technology hosted by Prof. George Piliouras. 

Learning to Remove Cuts in Integer Linear Programming

2024. 41st International Conference on Machine Learning (ICML 2024).

Imitation Learning in Discounted Linear MDPs without exploration assumptions

2024. 41st International Conference on Machine Learning (ICML 2024).

Efficient Continual Finite-Sum Minimization

2024. 12th International Conference on Learning Representations (ICLR 2024).

Maximum Independent Set: Self-Training through Dynamic Programming

2023. 37th Conference on Neural Information Processing Systems (NeurIPS 2023)..

Semi Bandit Dynamics in Congestion Games: Convergence to Nash Equilibrium and No-Regret Guarantees.

2023. 40th International Conference on Machine Learning (ICML).

Alternation makes the adversary weaker in two-player games

2023. 37th Conference on Neural Information Processing Systems (NeurIPS 2023).

Efficient Online Clustering with Moving Costs

2023. 37th Conference on Neural Information Processing Systems (NeurIPS 2023).

Beyond Time-Average Convergence: Near-Optimal Uncoupled Online Learning via Clairvoyant Multiplicative Weights Update

2022. 36th Conference on Neural Information Processing Systems (NeurIPS 2022).

Adaptive Stochastic Variance Reduction for Non-convex Finite-Sum Minimization

2022. 36th Conference on Neural Information Processing Systems (NeurIPS).

Contact

e-mail address: Efstratios Skoulakis


EPFL people page


Access map