2 papers
stat.ML2024
Learning for Bandits under Action Erasures
Osama Hanna, Merve Karakas, Lin F. Yang +1
We consider a novel multi-arm bandit (MAB) setup, where a learner needs to communicate the actions to distributed agents over erasure channels, while the rewards for the actions ar…
cs.LG2022
Differentially Private Stochastic Linear Bandits: (Almost) for Free
Osama A. Hanna, Antonious M. Girgis, Christina Fragouli +1
In this paper, we propose differentially private algorithms for the problem of stochastic linear bandits in the central, local and shuffled models. In the central model, we achieve…