Prati
Achraf Azize
Achraf Azize
Inria, Univ. Lille
Potvrđena adresa e-pošte na inria.fr - Početna stranica
Naslov
Citirano
Citirano
Godina
When privacy meets partial information: A refined analysis of differentially private bandits
A Azize, D Basu
NeurIPS 2022, 2022
122022
Concentrated Differential Privacy for Bandits
A Azize, D Basu
2024 IEEE Conference on Secure and Trustworthy Machine Learning (SaTML), 78-109, 2024
2*2024
On the Complexity of Differentially Private Best-Arm Identification with Fixed Confidence
A Azize, M Jourdan, AA Marjani, D Basu
NeurIPS 2023, 2023
12023
How Much Does Each Datapoint Leak Your Privacy? Quantifying the Per-datum Membership Leakage
A Azize, D Basu
arXiv preprint arXiv:2402.10065, 2024
2024
Conservative Exploration for Policy Optimization via Off-Policy Policy Evaluation
P Daoudi, M Formoso, O Gaizi, A Azize, E Garcelon
arXiv preprint arXiv:2312.15458, 2023
2023
Rényi Differentially Private Bandits
A Azize, D Basu
AAAI Workshop on Privacy Preserving AI, 2023
2023
Conservative Optimistic Policy Optimization via Multiple Importance Sampling
A Azize, O Gaizi
arXiv preprint arXiv:2103.03307, 2021
2021
2024 IEEE Conference on Secure and Trustworthy Machine Learning (SaTML)| 979-8-3503-4950-4/24/$31.00© 2024 IEEE| DOI: 10.1109/SaTML59370. 2024.00043
U Aïvodji, G Anderson, R Anderson, S Aydore, A Azize, D Basu, ...
Sustav trenutno ne može provesti ovu radnju. Pokušajte ponovo kasnije.
Članci 1–8