Achraf Azize

According to our database, Achraf Azize authored at least 12 papers between 2021 and 2025.

Collaborative distances:

• Dijkstra number of four.
• Erdős number of four.

2025

Optimal Regret of Bernoulli Bandits under Global Differential Privacy.

Achraf Azize, Yulian Wu, Junya Honda, Francesco Orabona, Shinji Ito, Debabrota Basu

CoRR, May, 2025

Some Targets Are Harder to Identify than Others: Quantifying the Target-dependent Membership Leakage.

Achraf Azize, Debabrota Basu

Proceedings of the International Conference on Artificial Intelligence and Statistics, 2025

2024

Privacy-Utility Trade-offs in Sequential Decision-Making under Uncertainty. (Compromis entre confidentialité et utilité dans la prise de décision séquentielle dans l'incertain).

Achraf Azize

PhD thesis, 2024

Differentially Private Best-Arm Identification.

Achraf Azize, Marc Jourdan, Aymen Al Marjani, Debabrota Basu

CoRR, 2024

How Much Does Each Datapoint Leak Your Privacy? Quantifying the Per-datum Membership Leakage.

Achraf Azize, Debabrota Basu

CoRR, 2024

Concentrated Differential Privacy for Bandits.

Achraf Azize, Debabrota Basu

Proceedings of the IEEE Conference on Secure and Trustworthy Machine Learning, 2024

Open Problem: What is the Complexity of Joint Differential Privacy in Linear Contextual Bandits?

Achraf Azize, Debabrota Basu

Proceedings of the Thirty Seventh Annual Conference on Learning Theory, June 30, 2024

2023

Conservative Exploration for Policy Optimization via Off-Policy Policy Evaluation.

Paul Daoudi, Mathias Formoso, Othman Gaizi, Achraf Azize, Evrard Garcelon

CoRR, 2023

Interactive and Concentrated Differential Privacy for Bandits.

Achraf Azize, Debabrota Basu

CoRR, 2023

On the Complexity of Differentially Private Best-Arm Identification with Fixed Confidence.

Achraf Azize, Marc Jourdan, Aymen Al Marjani, Debabrota Basu

Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

2022

When Privacy Meets Partial Information: A Refined Analysis of Differentially Private Bandits.

Achraf Azize, Debabrota Basu

Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

2021

Conservative Optimistic Policy Optimization via Multiple Importance Sampling.

Achraf Azize, Othman Gaizi

CoRR, 2021