Search Results for author: Khaled Eldowa

Found 3 papers, 0 papers with code

Information Capacity Regret Bounds for Bandits with Mediator Feedback

no code implementations15 Feb 2024 Khaled Eldowa, Nicolò Cesa-Bianchi, Alberto Maria Metelli, Marcello Restelli

For a selection of policy set families, we prove nearly-matching lower bounds, scaling similarly with the capacity.

General Tail Bounds for Non-Smooth Stochastic Mirror Descent

no code implementations12 Dec 2023 Khaled Eldowa, Andrea Paudice

Finally, we support our theory with illustrative experiments that compare the behavior of the average of the iterates with that of the last iterate in heavy-tailed noise regimes.

Information-Theoretic Regret Bounds for Bandits with Fixed Expert Advice

no code implementations14 Mar 2023 Khaled Eldowa, Nicolò Cesa-Bianchi, Alberto Maria Metelli, Marcello Restelli

We investigate the problem of bandits with expert advice when the experts are fixed and known distributions over the actions.

Cannot find the paper you are looking for? You can Submit a new open access paper.