PAC Confidence Sets for Deep Neural Networks via Calibrated Prediction
- Title
- PAC Confidence Sets for Deep Neural Networks via Calibrated Prediction
- Authors
- PARK, SANGDON; Bastani, Osbert; Matni, Nikolai; Lee, Insup
- Date Issued
- 2020-04-26
- Publisher
- International Conference on Learning Representations
- 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.
- URI
- https://oasis.postech.ac.kr/handle/2014.oak/120015
- Article Type
- Conference
- Citation
- International Conference on Learning Representations, 2020-04-26
- Files in This Item:
- There are no files associated with this item.
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.