Hédi Hadiji

Since 2022, I am a tenure-track assistant professor (maître de conférences) at the Laboratoire des Signaux et Systèmes at CentraleSupélec. Prior to that, I was a post-doc in the team of Tim van Erven at the Korteweg-de Vries Institute for Mathematics, of the University of Amsterdam. I defended my PhD in 2020 at the LMO of the Université Paris-Saclay under the supervision of Gilles Stoltz and Pascal Massart.

My research interests lie broadly in the mathematics of online decision-making, focusing on adaptivity in bandits and online learning.

Office : 2nd floor at the IBM building
Mail : hedi.hadiji@l2s.centralesupelec.fr or hedi.hadiji@gmail.com


Research

Articles and preprints


An Online Feasible Point Method for Benign Generalized Nash Equilibrium Problems, with Sarah Sachs, Tim van Erven, and Mathias Staudigl 2024, under review [arxiv]

Tracking solutions of time-varying variational inequalities, with Sarah Sachs, and Cristóbal Guzmán, 2024, under review [arxiv]

Diversity-preserving K-armed bandits, revisited, with Sébastien Gerchinovitz, Jean-Michel Loubes, and Gilles Stoltz, 2024, Transactions on Machine Learning Research (TMLR) [Open Review] [Code]

Towards Characterizing the First-order Query Complexity of Learning (Approximate) Nash Equilibria in Zero-sum Matrix Games, with Wouter Koolen, Sarah Sachs, Tim van Erven, 2023, Neurips '23 [arxiv]

Accelerated Rates between Stochastic and Adversarial Online Convex Optimization, with Tim van Erven, Cristóbal Guzmán, and Sarah Sachs, 2023, (Extended version of our 2022 Neurips paper) [arxiv]

Scale-free Unconstrained Online Learning for Curved Losses, with Tim van Erven and Jack Mayo, 2022, Conference on Learning Theory (COLT) 2022 [arxiv] [slides]

Between Stochastic and Adversarial Online Convex Optimization: Improved Regret Bounds via Smoothness, with Tim van Erven, Cristóbal Guzmán, and Sarah Sachs, 2022, Advances in Neural Information Processing Systems (NeurIPS), 2022 [arxiv] [slides]

Distributed Online Learning for Joint Regret with Communication Constraints, with Tim van Erven and Dirk van der Hoeven, Algorithmic Learning Theory (ALT) 2022 [arxiv] [slides]

Adaptation to the Range in K-Armed Bandits, with Gilles Stoltz, Journal of Machine Learning Research, 2023 [HAL]

Polynomial Cost of Adaptation for X-armed Bandits, Advances in Neural Information Processing Systems (NeurIPS), 2019 [arxiv] [ poster]

KL-UCB-switch: Optimal Regret Bounds for Stochastic Bandits from both a Distribution-dependent and a Distribution-free Viewpoints, with Aurélien Garivier, Pierre Ménard and Gilles Stoltz, Journal of Machine Learning Research, 2022 [arxiv]

Talks


INRIA Fairplay seminar, Critéo, May 2024

DATAIA - ILLS workshop, CentraleSupélec, May 2023

Control Theory and Inverse Problems conference, Monastir, May 2023

LTCI S2A Seminar, Télécom Paris, July 2022

KdVI Statistics seminar, University of Amsterdam, March 2022

Séminaire de Mathématiques appliquées du Laboratoire Jean Leray, Université de Nantes February 2022

Weekly Machine Learning seminar, CWI, May 2021

Thematic Statistics Seminar in Machine Learning, Leiden University, February 2020

Seminar of the Institut für Mathematische Stochastik (IMST), Otto-von-Guericke-Universität, October 2019

Workshop of the Celeste INRIA team, INRIA September 2019

Séminaire des doctorants du Laboratoire de Mathématiques d'Orsay, Université Paris-Saclay, June 2019

50èmes Journées de Statistique, EDF Lab Paris Saclay, May 2018

Other


My PhD thesis, and the slides from my defense.

Reviewing services: COLT('23, '22, '21), UAI '21, Neurips'19 (top 400 reviewer), JMLR, Mathematics of Operations Research, SIMODS, Optimization Letters

I enjoy implementing the algorithms I design: my personal python bandit laboratory for numerical experiments.


Teaching

At CentraleSupélec

2023-2024:

  • Theoretical Foundations of Deep Learning (M2 Maths-IA -- 3rd year CS) [Class Webpage]
  • Introduction to Reinforcement Learning (3rd year CS)
  • Mathematical Refreshers (Bachelor AI and DS Management)
  • Ensemble Learning (TDs, Master Data and Science Business Analysis)
  • Analysis (TDs, Bachelor of Global Engineering)

2022-2023:

  • Introduction to Reinforcement Learning (3rd year CS)
  • Ensemble Learning (TDs, Master Data and Science Business Analysis)

Past

2020-2022: TA at University of Amsterdam

2019-2020: TA at Université Paris-Saclay (then Paris-Sud)

  • Mathematical Statistics (M1, 1st year Master's students) [webpage]
  • Statistics for Biologists, including R lab sessions (L2, 2nd year students)

2017-2019: TA at the IUT de Sceaux

  • Mathematics for Business, Mathematics and Personal Finance (1st year students)
  • Elementary Statistics (2nd year students)


Bio

  • 2022-   ...      Assistant Professor at CentraleSupélec
  • 2020-2022   Postdoc at the University of Amsterdam
  • 2017-2020   Ph.D. at the Laboratoire de Mathématiques d'Orsay
  • 2016-2017   Masters degree in Probability and Statistics at Université Paris-Saclay
  • 2015-2016   Part III of the Mathematical Tripos at the University of Cambridge
  • 2012-2016   Ecole polytechnique

Interests

I enjoy bouldering and I'd like to be better at chess. I read a lot of comics/graphic novels, and sometimes real books. When I feel free, I like to go to the movies.

My first name is Hédi and my last name is Hadiji. In Arabic my first name is written هادي. In English (and in French) pronounce my name like "Eddy".