@inproceedings{perrault2019exploiting,
abstract = {We improve the efficiency of algorithms for stochastic combinatorial semi-bandits. In most interesting problems, state-of-the-art algorithms take advantage of structural properties of rewards, such as independence. However, while being minimax optimal in terms of regret, these algorithms are intractable. In our paper, we first reduce their implementation to a specific submodular maximization. Then, in case of matroid constraints, we design adapted approximation routines, thereby providing the first efficient algorithms that exploit the reward structure. In particular, we improve the state-of-the-art efficient gap-free regret bound by a factor sqrt(k), where k is the maximum action size. Finally, we show how our improvement translates to more general budgeted combinatorial semi-bandits.},
archivePrefix = {arXiv},
arxivId = {1902.03794},
author = {Perrault, Pierre and Perchet, Vianney and Valko, Michal},
booktitle = {International Conference on Machine Learning},
eprint = {1902.03794},
month = {feb},
title = {{Exploiting structure of uncertainty for efficient matroid semi-bandits}},
year = {2019}
}