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 • NeurIPS 2023 • Mohammad Pedramfar, Christopher John Quinn, Vaneet Aggarwal
This paper presents a unified approach for maximizing continuous DR-submodular functions that encompasses a range of settings and oracle access types.
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 • 30 Jan 2023 • Guanyu Nie, Yididiya Y Nadew, Yanhui Zhu, Vaneet Aggarwal, Christopher John Quinn
The framework only requires the offline algorithms to be robust to small errors in function evaluation.