Hédi Hadiji

21 papers A* 5B 2Journal 14
YearRankTypeTitle / Venue / Authors
2025 B conf
An Online Feasible Point Method for Benign Generalized Nash Equilibrium Problems.
ALT
Sarah Sachs, Hédi Hadiji, Tim van Erven, Mathias Staudigl
2025 A* conf
Linear Bandits on Ellipsoids: Minimax Optimal Algorithms.
COLT
Raymond Zhang, Hédi Hadiji, Richard Combes
2025 J jnl
Linear Bandits on Ellipsoids: Minimax Optimal Algorithms.
CoRR
Raymond Zhang, Hédi Hadiji, Richard Combes
2025 J jnl
Tractable Instances of Bilinear Maximization: Implementing LinUCB on Ellipsoids.
CoRR
Raymond Zhang, Hédi Hadiji, Richard Combes
2024 J jnl
An Online Feasible Point Method for Benign Generalized Nash Equilibrium Problems.
CoRR
Sarah Sachs, Hédi Hadiji, Tim van Erven, Mathias Staudigl
2024 J jnl
Diversity-Preserving K-Armed Bandits, Revisited.
Trans. Mach. Learn. Res.
Hédi Hadiji, Sébastien Gerchinovitz, Jean-Michel Loubes, Gilles Stoltz
2024 J jnl
Tracking solutions of time-varying variational inequalities.
CoRR
Hédi Hadiji, Sarah Sachs, Cristóbal Guzmán
2023 J jnl
Adaptation to the Range in K-Armed Bandits.
J. Mach. Learn. Res.
Hédi Hadiji, Gilles Stoltz
2023 A* conf
Towards Characterizing the First-order Query Complexity of Learning (Approximate) Nash Equilibria in Zero-sum Matrix Games.
NeurIPS
Hédi Hadiji, Sarah Sachs, Tim van Erven, Wouter M. Koolen
2023 J jnl
Towards Characterizing the First-order Query Complexity of Learning (Approximate) Nash Equilibria in Zero-sum Matrix Games.
CoRR
Hédi Hadiji, Sarah Sachs, Tim van Erven, Wouter M. Koolen
2022 A* conf
Between Stochastic and Adversarial Online Convex Optimization: Improved Regret Bounds via Smoothness.
NeurIPS
Sarah Sachs, Hédi Hadiji, Tim van Erven, Cristóbal Guzmán
2022 J jnl
Between Stochastic and Adversarial Online Convex Optimization: Improved Regret Bounds via Smoothness.
CoRR
Sarah Sachs, Hédi Hadiji, Tim van Erven, Cristóbal Guzmán
2022 B conf
Distributed Online Learning for Joint Regret with Communication Constraints.
ALT
Dirk van der Hoeven, Hédi Hadiji, Tim van Erven
2022 J jnl
KL-UCB-Switch: Optimal Regret Bounds for Stochastic Bandits from Both a Distribution-Dependent and a Distribution-Free Viewpoints.
J. Mach. Learn. Res.
Aurélien Garivier, Hédi Hadiji, Pierre Ménard, Gilles Stoltz
2022 A* conf
Scale-free Unconstrained Online Learning for Curved Losses.
COLT
Jack J. Mayo, Hédi Hadiji, Tim van Erven
2022 J jnl
Scale-free Unconstrained Online Learning for Curved Losses.
CoRR
Jack J. Mayo, Hédi Hadiji, Tim van Erven
2021 J jnl
Distributed Online Learning for Joint Regret with Communication Constraints.
CoRR
Dirk van der Hoeven, Hédi Hadiji, Tim van Erven
2020 J jnl
Diversity-Preserving K-Armed Bandits, Revisited.
CoRR
Hédi Hadiji, Sébastien Gerchinovitz, Jean-Michel Loubes, Gilles Stoltz
2019 J jnl
Polynomial Cost of Adaptation for X -Armed Bandits.
CoRR
Hédi Hadiji
2019 A* conf
Polynomial Cost of Adaptation for X-Armed Bandits.
NeurIPS
Hédi Hadiji
2018 J jnl
KL-UCB-switch: optimal regret bounds for stochastic bandits from both a distribution-dependent and a distribution-free viewpoints.
CoRR
Aurélien Garivier, Hédi Hadiji, Pierre Ménard, Gilles Stoltz