|
|
Towards Characterizing the First-order Query Complexity of Learning (Approximate) Nash Equilibria in Zero-sum Matrix Games
Hédi Hadiji
,
Sarah Sachs
,
Tim van Erven
,
Wouter M. Koolen
Advances in Neural Information Processing Systems, 2023
Proceedings/Recueil des communications
hal-04079773v2
|
Partager
Gmail
Facebook
X
LinkedIn
More
|
|
|
On some adaptivity question in stochastic multi-armed bandits problems
Hédi Hadiji
Statistics [math.ST]. Université Paris-Saclay, 2020. English. ⟨NNT : ⟩
Thèse
tel-02941801v1
|
Partager
Gmail
Facebook
X
LinkedIn
More
|
|
|
Diversity-Preserving K-Armed Bandits, Revisited
Hédi Hadiji
,
Sébastien Gerchinovitz
,
Jean-Michel Loubes
,
Gilles Stoltz
2020
Pré-publication, Document de travail
hal-02957485v1
|
Partager
Gmail
Facebook
X
LinkedIn
More
|
|
|
Polynomial Cost of Adaptation for X -Armed Bandits
Hédi Hadiji
NeurIPS 2019 - Thirty-third Conference on Neural Information Processing Systems, Dec 2019, Vancouver, Canada
Communication dans un congrès
hal-02138492v2
|
Partager
Gmail
Facebook
X
LinkedIn
More
|
|
|
KL-UCB-switch: optimal regret bounds for stochastic bandits from both a distribution-dependent and a distribution-free viewpoints
Aurélien Garivier
,
Hédi Hadiji
,
Pierre Ménard
,
Gilles Stoltz
Journal of Machine Learning Research, 2022, 23 (179), pp.1-66
Article dans une revue
hal-01785705v3
|
Partager
Gmail
Facebook
X
LinkedIn
More
|
|
|
Adaptation to the Range in $K$-Armed Bandits
Hédi Hadiji
,
Gilles Stoltz
Journal of Machine Learning Research, 2023, 24 (13), pp.1-33
Article dans une revue
hal-02794382v3
|
Partager
Gmail
Facebook
X
LinkedIn
More
|