Waïss Azizian

Joined

September 2020

Names

Waïss Azizian (Preferred)

Emails

****@ens.fr (Confirmed)

****@univ-grenoble-alpes.fr (Confirmed)

Personal Links

Career & Education History

PhD student

Université Grenobel Alpes (univ-grenoble-alpes.fr)

2022 – 2025

MS student

Ecole Normale Supérieure de Paris (ens.fr)

2018 – 2021

Advisors, Relations & Conflicts

Family

Ieva Petrulionytė

Present

PhD Advisor

Panayotis Mertikopoulos

2020 – 2025

PhD Advisor

Jérôme Malick

2020 – 2025

PhD Advisor

Franck Iutzeler

2020 – 2025

Coauthor

Marc Lelarge

2021 – 2023

Expertise

Stochastic Optimization

Present

Robust Optimization

Present

Min-Max optimization

Present

Publications

How Does the Pretraining Distribution Shape In-Context Learning? Task Selection, Robustness and Generalization
Waïss Azizian, Ali Hasan
- Submitted to ICLR 2026
- Readers: Everyone
The Geometries of Truth Are Orthogonal Across Tasks
Waïss Azizian, Michael Kirchhof, Eugene Ndiaye, Louis Béthune, Michal Klein, Pierre Ablin, marco cuturi
- ICML 2025 R2-FM Workshop Poster
- Readers: Everyone
The Global Convergence Time of Stochastic Gradient Descent in Non-Convex Landscapes: Sharp Estimates via Large Deviations
Waïss Azizian, Franck Iutzeler, Jerome Malick, Panayotis Mertikopoulos
- ICML 2025 poster
- Readers: Everyone
Almost Sure Convergence of Stochastic Gradient Methods under Gradient Domination
Simon Weissmann, Sara Klein, Waïss Azizian, Leif Döring
- Accepted by TMLR
- Readers: Everyone
Almost Sure Convergence of Stochastic Gradient Methods under Gradient Domination
Simon Weissmann, Sara Klein, Waïss Azizian, Leif Döring
- EWRL17
- Readers: Everyone
What is the Long-Run Distribution of Stochastic Gradient Descent? A Large Deviations Analysis
Waïss Azizian, Franck Iutzeler, Jerome Malick, Panayotis Mertikopoulos
- ICML 2024 Poster
- Readers: Everyone
Automatic Rao-Blackwellization for Sequential Monte Carlo with Belief Propagation
Waïss Azizian, Guillaume Baudart, Marc Lelarge
- 1st SPIGM @ ICML Poster
- Readers: Everyone
Exact Generalization Guarantees for (Regularized) Wasserstein Distributionally Robust Models
Waïss Azizian, Franck Iutzeler, Jérôme Malick
- NeurIPS 2023 poster
- Readers: Everyone
On the rate of convergence of Bregman proximal methods in constrained variational inequalities
Waïss Azizian, Franck Iutzeler, Jérôme Malick, Panayotis Mertikopoulos
- 2022 (modified: 14 Jan 2023)
- CoRR 2022
- Readers: Everyone
A Tight and Unified Analysis of Gradient-Based Methods for a Whole Spectrum of Differentiable Games
Waïss Azizian, Ioannis Mitliagkas, Simon Lacoste-Julien, Gauthier Gidel
- 24 May 2021
- OpenReview Archive Direct Upload
- Readers: Everyone

View all 21 publications

Waïss Azizian

Names

Emails

Personal Links

Career & Education History

Advisors, Relations & Conflicts

Expertise

Publications

Co-Authors