Hédi Hadiji

Publication Activity (10 Years)

Years Active: 2018-2024
Publications (10 Years): 17

Top Topics

Nash Equilibria

Online Learning

Query Complexity

Top Venues

J. Mach. Learn. Res.

Publications

Hédi Hadiji, Sébastien Gerchinovitz, Jean-Michel Loubes, Gilles Stoltz
Diversity-Preserving K-Armed Bandits, Revisited. Trans. Mach. Learn. Res. 2024 (2024)
Hédi Hadiji, Sarah Sachs, Cristóbal Guzmán
Tracking solutions of time-varying variational inequalities. CoRR (2024)
Hédi Hadiji, Sarah Sachs, Tim van Erven, Wouter M. Koolen
Towards Characterizing the First-order Query Complexity of Learning (Approximate) Nash Equilibria in Zero-sum Matrix Games. CoRR (2023)
Hédi Hadiji, Sarah Sachs, Tim van Erven, Wouter M. Koolen
Towards Characterizing the First-order Query Complexity of Learning (Approximate) Nash Equilibria in Zero-sum Matrix Games. NeurIPS (2023)
Hédi Hadiji, Gilles Stoltz
Adaptation to the Range in K-Armed Bandits. J. Mach. Learn. Res. 24 (2023)
Sarah Sachs, Hédi Hadiji, Tim van Erven, Cristóbal Guzmán
Accelerated Rates between Stochastic and Adversarial Online Convex Optimization. CoRR (2023)
Sarah Sachs, Hédi Hadiji, Tim van Erven, Cristóbal Guzmán
Between Stochastic and Adversarial Online Convex Optimization: Improved Regret Bounds via Smoothness. NeurIPS (2022)
Jack J. Mayo, Hédi Hadiji, Tim van Erven
Scale-free Unconstrained Online Learning for Curved Losses. CoRR (2022)
Sarah Sachs, Hédi Hadiji, Tim van Erven, Cristóbal Guzmán
Between Stochastic and Adversarial Online Convex Optimization: Improved Regret Bounds via Smoothness. CoRR (2022)
Dirk van der Hoeven, Hédi Hadiji, Tim van Erven
Distributed Online Learning for Joint Regret with Communication Constraints. ALT (2022)
Aurélien Garivier, Hédi Hadiji, Pierre Ménard, Gilles Stoltz
KL-UCB-Switch: Optimal Regret Bounds for Stochastic Bandits from Both a Distribution-Dependent and a Distribution-Free Viewpoints. J. Mach. Learn. Res. 23 (2022)
Jack J. Mayo, Hédi Hadiji, Tim van Erven
Scale-free Unconstrained Online Learning for Curved Losses. COLT (2022)
Dirk van der Hoeven, Hédi Hadiji, Tim van Erven
Distributed Online Learning for Joint Regret with Communication Constraints. CoRR (2021)
Hédi Hadiji, Sébastien Gerchinovitz, Jean-Michel Loubes, Gilles Stoltz
Diversity-Preserving K-Armed Bandits, Revisited. CoRR (2020)
Hédi Hadiji
Polynomial Cost of Adaptation for X-Armed Bandits. NeurIPS (2019)
Hédi Hadiji
Polynomial Cost of Adaptation for X -Armed Bandits. CoRR (2019)
Aurélien Garivier, Hédi Hadiji, Pierre Ménard, Gilles Stoltz
KL-UCB-switch: optimal regret bounds for stochastic bandits from both a distribution-dependent and a distribution-free viewpoints. CoRR (2018)