Dr. Ali Ramezani-Kebrya (2021-2022)

Research Interests:

  • Large-scale and distributed machine learning 
  • Optimization
  • Privacy/security 
  • Reinforcement learning 
  • Communications/networking 

Biography

Ali Ramazani-Kebraya is currently an Associate Professor (with tenure) in CS at the University of Oslo. He was a postdoctoral fellow at LIONS. Before joining EPFL, he was a postdoctoral fellow at the Vector Institute in Canada. He works in machine learning and studies communication, optimization, privacy/security, and generalization aspects of machine learning algorithms. Ali received his Ph.D. from the University of Toronto. He is a recipient of the Natural Sciences and Engineering Research Council of Canada Postdoctoral Fellowship, which is equivalent to NSF fellowship in the US.

Publications with LIONS

Layer-wise Quantization for Quantized Optimistic Dual Averaging

A. Duc Nguyen; I. Markov; F. Z. Wu; A. Ramezani-Kebrya; K. Antonakopoulos et al. 

2025. Forty-Second International Conference on Machine Learning, Vancouver, Canada, 2025-07-13 – 2025-07-19.

Detailed record

Addressing Label Shift In Distributed Learning Via Entropy Regularization

Z. Wu; C. Choi; X. Cao; V. Cevher; A. Ramezani-Kebrya 

2025. The Thirteenth International Conference on Learning Representations, Singapore, 2025-04-24-2025-04-28.

Detailed record

Mixed Nash for Robust Federated Learning

W. Xie; T. M. Pethick; A. Ramezani-Kebrya; V. Cevher 

Transactions on Machine Learning Research. 2024. Vol. 02.

Detailed record

On the Generalization of Stochastic Gradient Descent with Momentum

A. Ramezani-Kebrya; K. Antonakopoulos; V. Cevher; A. Khisti; B. Liang 

Journal of Machine Learning Research. 2024. Vol. 25, p. 1 – 56.

Detailed record

Distributed Extra-Gradient With Optimal Complexity And Communication Guarantees

A. Ramezani-Kebrya; K. Antonakopoulos; I. Krawczuk; J. Deschenaux; V. Cevher 

2023. 11th International Conference on Learning Representations (ICLR), Kigali, Rwanda, May 1-5, 2023.

Detailed record