DC Field | Value | Language |
---|---|---|
dc.contributor.author | Park, Sangdon | - |
dc.contributor.author | Dobriban, Edgar | - |
dc.contributor.author | Lee, Insup | - |
dc.contributor.author | Bastani, Osbert | - |
dc.date.accessioned | 2024-02-01T01:54:17Z | - |
dc.date.available | 2024-02-01T01:54:17Z | - |
dc.date.created | 2024-01-30 | - |
dc.date.issued | 2022-12-02 | - |
dc.identifier.uri | https://oasis.postech.ac.kr/handle/2014.oak/120008 | - |
dc.description.abstract | Uncertainty quantification is a key component of machine learning models targeted at safety-critical systems such as in healthcare or autonomous vehicles. We study this problem in the context of meta learning, where the goal is to quickly adapt a predictor to new tasks. In particular, we propose a novel algorithm to construct PAC prediction sets, which capture uncertainty via sets of labels, that can be adapted to new tasks with only a few training examples. These prediction sets satisfy an extension of the typical PAC guarantee to the meta learning setting; in particular, the PAC guarantee holds with high probability over future tasks. We demonstrate the efficacy of our approach on four datasets across three application domains: mini-ImageNet and CIFAR10-C in the visual domain, FewRel in the language domain, and the CDC Heart Dataset in the medical domain. In particular, our prediction sets satisfy the PAC guarantee while having smaller size compared to other baselines that also satisfy this guarantee. | - |
dc.language | English | - |
dc.publisher | Neural information processing systems foundation | - |
dc.relation.isPartOf | 36th Conference on Neural Information Processing Systems, NeurIPS 2022 | - |
dc.relation.isPartOf | Advances in Neural Information Processing Systems | - |
dc.title | PAC Prediction Sets for Meta-Learning | - |
dc.type | Conference | - |
dc.type.rims | CONF | - |
dc.identifier.bibliographicCitation | 36th Conference on Neural Information Processing Systems, NeurIPS 2022 | - |
dc.citation.conferenceDate | 2022-11-28 | - |
dc.citation.conferencePlace | US | - |
dc.citation.title | 36th Conference on Neural Information Processing Systems, NeurIPS 2022 | - |
dc.contributor.affiliatedAuthor | Park, Sangdon | - |
dc.description.journalClass | 1 | - |
dc.description.journalClass | 1 | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.
library@postech.ac.kr Tel: 054-279-2548
Copyrights © by 2017 Pohang University of Science ad Technology All right reserved.