Leello Tadesse Dadi (2025)

Research Interests:

  • Optimization
  • Algorithms and Randomness.

 

Biography

I studied Applied Mathematics and Computer Science at Télécom ParisTech. I obtained my MSc degree from ENS Paris-Saclay in 2019.  

Generalization of Noisy SGD in Unbounded Non-convex Settings

L. Dadi; V. Cevher 

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

Detailed record

Faster Inference Of Flow-Based Generative Models Via Improved Data-Noise Coupling

A. Davtyan; L. T. Dadi; V. Cevher; P. Favaro 

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

Detailed record

Learning with Norm Constrained, Over-parameterized, Two-layer Neural Networks

F. Liu; L. Dadi; V. Cevher 

Journal of Machine Learning Research. 2024. Vol. 25.

Detailed record

Efficient Continual Finite-Sum Minimization

I. Mavrothalassitis; E. P. Skoulakis; L. T. Dadi; V. Cevher 

2024. 12th International Conference on Learning Representations (ICLR 2024), Vienna, Austria, May 7-11, 2024.

Detailed record

Finding Actual Descent Directions For Adversarial Training

F. Latorre; I. Krawczuk; L. T. Dadi; T. M. Pethick; V. Cevher 

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

Detailed record