I am a PhD student at EPFL working on trustworthy machine learning. My research interests include robustness, privacy, and unlearning, especially within distributed and collaborative learning environments. I graduated from Ecole Polytechnique in Mathematics and Computer Science, and have also conducted research at Amazon and Stanford University.

Selected Publications

The Utility and Complexity of In- and Out-of-Distribution Machine Unlearning [paper]
Y. Allouah, J. Kazdan, R. Guerraoui, S. Koyejo. ICLR 2025

The Privacy Power of Correlated Noise in Decentralized Learning [paper][code]
Y. Allouah, A. Koloskova, A. El Firdoussi, M. Jaggi, R. Guerraoui. ICML 2024

Robust Distributed Learning: Tight Error Bounds and Breakdown Point under Data Heterogeneity [paper][code][video]
Y. Allouah, R. Guerraoui, N. Gupta, R. Pinot, G. Rizk. NeurIPS 2023, Spotlight

On the Privacy-Robustness-Utility Trilemma in Distributed Learning [paper][video]
Y. Allouah, R. Guerraoui, N. Gupta, R. Pinot, J. Stephan. ICML 2023

Robust Sparse Voting [paper][code]
Y. Allouah, R. Guerraoui, L. Hoang, O. Villemaud. AISTATS 2024

Fixing by Mixing: a Recipe for Optimal Byzantine ML under Heterogeneity [paper]
Y. Allouah, S. Farhadkhani, R. Guerraoui, N. Gupta, R. Pinot, J. Stephan. AISTATS 2023

Latent Discourse Models and Word Embeddings [paper]
S. Khalife, D. Gonçalves, Y. Allouah, L. Liberti. JMLR 2021

Talks

Trustworthy Machine Learning [video] UM6P College of Computing, 2024
Trustworthy Machine Learning: Robustness and Privacy [video] MoroccoAI Seminar, 2023
Robust Sparse Voting [video] PODC 2022; Tournesol Talks, 2023