%0 Journal Article %1 pacchiano2020robustness %A Pacchiano, Aldo %A Jiang, Heinrich %A Jordan, Michael I. %D 2020 %K bandits bayesian readings robustness %T Robustness Guarantees for Mode Estimation with an Application to Bandits %U http://arxiv.org/abs/2003.02932 %X Mode estimation is a classical problem in statistics with a wide range of applications in machine learning. Despite this, there is little understanding in its robustness properties under possibly adversarial data contamination. In this paper, we give precise robustness guarantees as well as privacy guarantees under simple randomization. We then introduce a theory for multi-armed bandits where the values are the modes of the reward distributions instead of the mean. We prove regret guarantees for the problems of top arm identification, top m-arms identification, contextual modal bandits, and infinite continuous arms top arm recovery. We show in simulations that our algorithms are robust to perturbation of the arms by adversarial noise sequences, thus rendering modal bandits an attractive choice in situations where the rewards may have outliers or adversarial corruptions.

@article{pacchiano2020robustness, abstract = {Mode estimation is a classical problem in statistics with a wide range of applications in machine learning. Despite this, there is little understanding in its robustness properties under possibly adversarial data contamination. In this paper, we give precise robustness guarantees as well as privacy guarantees under simple randomization. We then introduce a theory for multi-armed bandits where the values are the modes of the reward distributions instead of the mean. We prove regret guarantees for the problems of top arm identification, top m-arms identification, contextual modal bandits, and infinite continuous arms top arm recovery. We show in simulations that our algorithms are robust to perturbation of the arms by adversarial noise sequences, thus rendering modal bandits an attractive choice in situations where the rewards may have outliers or adversarial corruptions.}, added-at = {2020-03-12T13:40:11.000+0100}, author = {Pacchiano, Aldo and Jiang, Heinrich and Jordan, Michael I.}, biburl = {https://www.bibsonomy.org/bibtex/20267d49642dde76567c22cdb10eeb543/kirk86}, description = {[2003.02932] Robustness Guarantees for Mode Estimation with an Application to Bandits}, interhash = {83b4b235f00e10116f4b127470678329}, intrahash = {0267d49642dde76567c22cdb10eeb543}, keywords = {bandits bayesian readings robustness}, note = {cite arxiv:2003.02932Comment: 12 pages, 7 figures, 14 appendix pages}, timestamp = {2020-03-12T13:40:11.000+0100}, title = {Robustness Guarantees for Mode Estimation with an Application to Bandits}, url = {http://arxiv.org/abs/2003.02932}, year = 2020 }