Zobrazeno 1 - 7
of 7
pro vyhledávání: '"Azize, Achraf"'
Best Arm Identification (BAI) problems are progressively used for data-sensitive applications, such as designing adaptive clinical trials, tuning hyper-parameters, and conducting user studies. Motivated by the data privacy concerns invoked by these a
Externí odkaz:
http://arxiv.org/abs/2406.06408
Autor:
Azize, Achraf, Basu, Debabrota
We study the per-datum Membership Inference Attacks (MIAs), where an attacker aims to infer whether a fixed target datum has been included in the input dataset of an algorithm and thus, violates privacy. First, we define the membership leakage of a d
Externí odkaz:
http://arxiv.org/abs/2402.10065
A precondition for the deployment of a Reinforcement Learning agent to a real-world system is to provide guarantees on the learning process. While a learning algorithm will eventually converge to a good policy, there are no guarantees on the performa
Externí odkaz:
http://arxiv.org/abs/2312.15458
Best Arm Identification (BAI) problems are progressively used for data-sensitive applications, such as designing adaptive clinical trials, tuning hyper-parameters, and conducting user studies to name a few. Motivated by the data privacy concerns invo
Externí odkaz:
http://arxiv.org/abs/2309.02202
Autor:
Azize, Achraf, Basu, Debabrota
Bandits serve as the theoretical foundation of sequential learning and an algorithmic foundation of modern recommender systems. However, recommender systems often rely on user-sensitive data, making privacy a critical concern. This paper contributes
Externí odkaz:
http://arxiv.org/abs/2309.00557
Autor:
Azize, Achraf, Basu, Debabrota
We study the problem of multi-armed bandits with $\epsilon$-global Differential Privacy (DP). First, we prove the minimax and problem-dependent regret lower bounds for stochastic and linear bandits that quantify the hardness of bandits with $\epsilon
Externí odkaz:
http://arxiv.org/abs/2209.02570
Autor:
Azize, Achraf, Gaizi, Othman
Reinforcement Learning (RL) has been able to solve hard problems such as playing Atari games or solving the game of Go, with a unified approach. Yet modern deep RL approaches are still not widely used in real-world applications. One reason could be t
Externí odkaz:
http://arxiv.org/abs/2103.03307