no code implementations • 9 May 2024 • Fares Fourati, Mohamed-Slim Alouini, Vaneet Aggarwal
Additionally, the algorithm is notably communication-efficient, requiring only a sublinear number of communication rounds, quantified as $\tilde{\mathcal{O}}\left(\psi T^\frac{\beta}{\beta+1}\right)$.
no code implementations • 1 Feb 2024 • Ahmed Radwan, Layan Zaafarani, Jetana Abudawood, Faisal AlZahrani, Fares Fourati
Addressing biases in AI models is crucial for ensuring fair and accurate predictions.
no code implementations • 13 Dec 2023 • Fares Fourati, Christopher John Quinn, Mohamed-Slim Alouini, Vaneet Aggarwal
We propose a novel combinatorial stochastic-greedy bandit (SGB) algorithm for combinatorial multi-armed bandit problems when no extra information other than the joint reward of the selected set of $n$ arms at each time step $t\in [T]$ is observed.
no code implementations • 13 Feb 2023 • Fares Fourati, Salma Kharrat, Vaneet Aggarwal, Mohamed-Slim Alouini, Marco Canini
Federated learning is an emerging machine learning paradigm that enables clients to train collaboratively without exchanging local data.
no code implementations • 2 Feb 2023 • Fares Fourati, Vaneet Aggarwal, Christopher John Quinn, Mohamed-Slim Alouini
We investigate the problem of unconstrained combinatorial multi-armed bandits with full-bandit feedback and stochastic rewards for submodular maximization.
no code implementations • 25 Feb 2022 • Fares Fourati, Saeed Hamood Alsamhi, Mohamed-Slim Alouini
Connectivity in rural areas is one of the main challenges of communication networks.
no code implementations • 25 Jan 2021 • Fares Fourati, Mohamed-Slim Alouini
Satellite communication offers the prospect of service continuity over uncovered and under-covered areas, service ubiquity, and service scalability.
no code implementations • 24 Sep 2020 • Fares Fourati, Wided Souidene, Rabah Attia
We emphasize on optimizing the performance of our proposed final architectures.