Matches in Ghent University Academic Bibliography for { <https://biblio.ugent.be/publication/01H9MQE57P35HAXZQEE2V7DCYT> ?p ?o. }
Showing items 1 to 24 of
24
with 100 items per page.
- 01H9MQE57P35HAXZQEE2V7DCYT classification P1.
- 01H9MQE57P35HAXZQEE2V7DCYT date "2023".
- 01H9MQE57P35HAXZQEE2V7DCYT language "eng".
- 01H9MQE57P35HAXZQEE2V7DCYT type conference.
- 01H9MQE57P35HAXZQEE2V7DCYT hasPart 01H9MS9NW43WJZQCSXRGBQ5EHN.pdf.
- 01H9MQE57P35HAXZQEE2V7DCYT subject "Mathematics and Statistics".
- 01H9MQE57P35HAXZQEE2V7DCYT subject "Technology and Engineering".
- 01H9MQE57P35HAXZQEE2V7DCYT issn "2640-3498".
- 01H9MQE57P35HAXZQEE2V7DCYT presentedAt urn:uuid:15b9dceb-ebce-4b1b-bee4-e90d6b0fd6c8.
- 01H9MQE57P35HAXZQEE2V7DCYT volume "202".
- 01H9MQE57P35HAXZQEE2V7DCYT abstract " It is well known that accurate probabilistic predictors can be trained through empirical risk minimisation with proper scoring rules as loss functions. While such learners capture so-called aleatoric uncertainty of predictions, various machine learning methods have recently been developed with the goal to let the learner also represent its epistemic uncertainty, i.e., the uncertainty caused by a lack of knowledge and data. An emerging branch of the literature proposes the use of a second-order learner that provides predictions in terms of distributions on probability distributions. However, recent work has revealed serious theoretical shortcomings for second-order predictors based on loss minimisation. In this paper, we generalise these findings and prove a more fundamental result: There seems to be no loss function that provides an incentive for a second-order learner to faithfully represent its epistemic uncertainty in the same manner as proper scoring rules do for standard (first-order) learners. As a main mathematical tool to prove this result, we introduce the generalised notion of second-order scoring rules. ".
- 01H9MQE57P35HAXZQEE2V7DCYT author F71947FE-F0ED-11E1-A9DE-61C894A0A6B4.
- 01H9MQE57P35HAXZQEE2V7DCYT author urn:uuid:0298318b-922a-4929-81f5-c8c1a38ac98c.
- 01H9MQE57P35HAXZQEE2V7DCYT author urn:uuid:86f98494-23c1-40fc-aa0c-b0e6a49179cd.
- 01H9MQE57P35HAXZQEE2V7DCYT dateCreated "2023-09-06T07:48:46Z".
- 01H9MQE57P35HAXZQEE2V7DCYT dateModified "2025-01-06T08:49:09Z".
- 01H9MQE57P35HAXZQEE2V7DCYT editor F71947FE-F0ED-11E1-A9DE-61C894A0A6B4.
- 01H9MQE57P35HAXZQEE2V7DCYT editor urn:uuid:1cff636f-ff4e-4e0b-9068-01bddf94a7ff.
- 01H9MQE57P35HAXZQEE2V7DCYT editor urn:uuid:399a4426-4dde-42fc-b1c1-0568224e39f1.
- 01H9MQE57P35HAXZQEE2V7DCYT name "On second-order scoring rules for epistemic uncertainty quantification".
- 01H9MQE57P35HAXZQEE2V7DCYT pagination urn:uuid:edfa2d9d-7eb1-4908-bbf4-26e22c426a7a.
- 01H9MQE57P35HAXZQEE2V7DCYT sameAs LU-01H9MQE57P35HAXZQEE2V7DCYT.
- 01H9MQE57P35HAXZQEE2V7DCYT sourceOrganization urn:uuid:d351d805-d482-4f61-85c7-502d309340f4.
- 01H9MQE57P35HAXZQEE2V7DCYT type P1.