02/02/2021

Robustness Guarantees for Mode Estimation with an Application to Bandits

Aldo Pacchiano, Heinrich Jiang, Michael I. Jordan

Keywords:

Abstract Paper Similar Papers

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.

The video of this talk cannot be embedded. You can watch it here:
https://slideslive.com/38948984
(Link will open in new window)
 0
 0
 0
 0
  Share    
This is an embedded video. Talk and the respective paper are published at AAAI 2021 virtual conference. If you are one of the authors of the paper and want to manage your upload, see the question "My papertalk has been externally embedded..." in the FAQ section.

Comments

Post Comment
no comments yet
code of conduct: tbd Characters remaining: 140

Similar Papers

 0
 0
 0
 0
 14:31 
 0
 0
 0
 0
 3:25 
 0
 0
 0
 0
 2:48 
 0
 0
 0
 0
 11:41 
 0
 0
 0
 2
 4:57 
 0
 0
 0
 0
 14:47 
 0
 0
 0
 0
 4:58 
 0
 0
 0
 0
 2:58 
 0
 0
 0
 0
 12:01 
 0
 0
 0
 0
 18:49 
 0
 0
 0
 0
 3:30 
 0
 0
 0
 0
 10:53 
 0
 0
 0
 0
 17:11 
 0
 0
 0
 0
 1:01 
 0
 0
 0
 0
 4:49 
 0
 0
 0
 0
 14:29 
 0
 0
 0
 0
 3:24 
 0
 0
 0
 0
 5:30 
 0
 0
 0
 0
 3:23 
 0
 0
 0
 0
 16:38 
 0
 0
 0
 0
 20:29 
 0
 0
 0
 0
 5:02 
 0
 0
 0
 0
 10:49 
 0
 0
 0
 0
 14:59 
 0
 0
 0
 0
 15:40 
 0
 0
 0
 0
 3:16 
 0
 0
 0
 0
 5:13 
 0
 0
 0
 0
 3:11 
 0
 0
 0
 0
 14:36 
 0
 0
 0
 0
 16:07 
 0
 0
 0
 0
 4:17 
 0
 0
 0
 0
 17:20 
 0
 0
 0
 0
 3:01 
 0
 0
 0
 0
 15:13 
 0
 0
 0
 0
 5:14 
 0
 0
 0
 0
 4:54 
 0
 0
 0
 0
 15:33 
 0
 0
 0
 0
 12:36 
 0
 0
 0
 0
 2:57 
 0
 0
 0
 0
 9:14