26/04/2020

PAC Confidence Sets for Deep Neural Networks via Calibrated Prediction

Sangdon Park, Osbert Bastani, Nikolai Matni, Insup Lee

Keywords: PAC, confidence sets, classification, regression, reinforcement learning

Abstract Paper Code Similar Papers

Abstract: We propose an algorithm combining calibrated prediction and generalization bounds from learning theory to construct confidence sets for deep neural networks with PAC guarantees---i.e., the confidence set for a given input contains the true label with high probability. We demonstrate how our approach can be used to construct PAC confidence sets on ResNet for ImageNet, a visual object tracking model, and a dynamics model for the half-cheetah reinforcement learning problem.

 0
 0
 0
 0
  Share    
This is an embedded video. Talk and the respective paper are published at ICLR 2020 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
 3:13 
 0
 0
 0
 0
 10:52 
 1
 1
 0
 0
 15:53 
 0
 0
 0
 0
 5:14 
 0
 0
 0
 0
 3:15 
 0
 0
 0
 0
 3:50 
 0
 0
 0
 1
 5:06 
 0
 0
 0
 0
 3:20 
 0
 0
 0
 0
 3:11 
 0
 0
 0
 0
 11:25 
 0
 0
 0
 0
 3:26 
 0
 0
 0
 0
 14:49 
 0
 0
 0
 0
 18:48 
 0
 0
 0
 0
 3:20 
 0
 0
 0
 0
 4:31 
 0
 0
 0
 0
 5:08 
 0
 0
 0
 0
 3:20 
 0
 0
 0
 0
 5:00 
 0
 0
 0
 0
 14:45 
 0
 0
 0
 0
 4:32 
 0
 0
 0
 0
 3:21 
 0
 0
 0
 0
 3:25 
 0
 0
 0
 0
 5:15 
 0
 0
 0
 0
 4:33 
 0
 0
 0
 0
 13:51 
 0
 0
 0
 0
 3:02 
 0
 0
 0
 0
 13:45 
 0
 0
 0
 0
 7:45 
 0
 0
 0
 0
 5:12 
 0
 0
 0
 0
 15:23 
 0
 0
 0
 0
 8:19 
 0
 0
 0
 0
 3:13 
 0
 0
 0
 0
 3:10 
 0
 0
 0
 0
 5:21 
 0
 0
 0
 0
 5:09 
 0
 0
 0
 0
 12:47 
 0
 0
 0
 0
 4:27 
 0
 0
 0
 0
 14:35 
 0
 0
 0
 0
 13:26 
 0
 0
 0
 0
 3:24