Hamza Cherkaoui

Télécom SudParis

Paris, France

I develop theoretically grounded diffusion and flow-matching methods for reliable generative modeling under long-tailed data distributions, with an emphasis on rare-mode coverage, transfer, and reproducible large-scale evaluation.

I am a postdoctoral researcher at Télécom SudParis, where I work with Prof. Hélène Halconruy. My work combines mathematical analysis with reproducible PyTorch/SLURM research pipelines and empirical benchmarks.

Previously, I worked at Noah’s Ark Lab, Huawei Technologies in Paris, with Dr. Igor Colin. I completed my Ph.D. in the Parietal team at CEA, advised by Dr. Philippe Ciuciu, Dr. Claire Leroy, and Dr. Thomas Moreau.

For more details, see my CV, Google Scholar, and GitHub; you can also contact me by email.

research themes

Generative modeling and flow matching. Reliable and diverse generation.
Long-tail distributions and rare modes. Understanding and improving coverage of underrepresented structure.
Transfer learning and source selection. Avoiding negative transfer and identifying useful source tasks.

selected papers

Preprint, 2026	Do Heavy Tails Help Diffusion? On the Subtle Trade-off Between Initialization and Training paper Analyzes the trade-off between heavy-tailed initialization, training error, tail coverage, and sample diversity in diffusion and flow-based models.
Preprint, 2026	When to Transfer: Adaptive Source Selection for Positive Transfer in Linear Models paper Introduces a data-driven sample-sharing rule for using auxiliary data while protecting against negative transfer in ridge regression.
Poster, AISTATS, 2026	High-Dimensional Analysis of Bootstrap Ensemble Classifiers paper code Uses random matrix theory to analyze bootstrap LSSVM ensembles and derive practical choices for subset selection and regularization.
Poster, ICML, 2025	Adaptive Sample Sharing for Multi Agent Linear Bandits paper Studies data sharing in multi-agent linear bandits and formalizes the bias-uncertainty trade-off behind collaboration.

news

May 14, 2026	Our work High-Dimensional Analysis of Bootstrap Ensemble Classifiers was presented as a poster at AISTATS 2026 in Tangier.
Jul 14, 2025	I presented our work Adaptive Sample Sharing for Multi Agent Linear Bandits as a poster at ICML 2025 in Vancouver.
Jun 15, 2025	I joined Télécom SudParis as a postdoctoral researcher with Prof. Hélène Halconruy.