On Discriminative Learning of Prediction Uncertainty
The result's identifiers
Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21230%2F19%3A00334290" target="_blank" >RIV/68407700:21230/19:00334290 - isvavai.cz</a>
Result on the web
<a href="http://proceedings.mlr.press/v97/franc19a/franc19a.pdf" target="_blank" >http://proceedings.mlr.press/v97/franc19a/franc19a.pdf</a>
DOI - Digital Object Identifier
—
Alternative languages
Result language
angličtina
Original language name
On Discriminative Learning of Prediction Uncertainty
Original language description
In classification with a reject option, the classifier is allowed in uncertain cases to abstain from prediction. The classical cost based model of an optimal classifier with a reject option requires the cost of rejection to be defined explicitly. An alternative bounded-improvement model, avoiding the notion of the reject cost, seeks for a classifier with a guaranteed selective risk and maximal cover. We prove that both models share the same class of optimal strategies, and we provide an explicit relation between the reject cost and the target risk being the parameters of the two models. An optimal rejection strategy for both models is based on thresholding the conditional risk defined by posterior probabilities which are usually unavailable. We propose a discriminative algorithm learning an uncertainty function which preserves ordering of the input space induced by the conditional risk, and hence can be used to construct optimal rejection strategies.
Czech name
—
Czech description
—
Classification
Type
D - Article in proceedings
CEP classification
—
OECD FORD branch
10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)
Result continuities
Project
Result was created during the realization of more than one project. More information in the Projects tab.
Continuities
P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)
Others
Publication year
2019
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů
Data specific for result type
Article name in the collection
International Conference on Machine Learning
ISBN
978-1-5108-8698-8
ISSN
2640-3498
e-ISSN
—
Number of pages
16
Pages from-to
3465-3480
Publisher name
Proceedings of Machine Learning Research
Place of publication
—
Event location
Long Beach
Event date
Jun 10, 2019
Type of event by nationality
WRD - Celosvětová akce
UT code for WoS article
—