Matches in SemOpenAlex for { <https://semopenalex.org/work/W4386980312> ?p ?o ?g. }
Showing items 1 to 88 of
88
with 100 items per page.
- W4386980312 abstract "Abstract Performance of classifiers is often measured in terms of average accuracy on test data. Despite being a standard measure, average accuracy fails in characterising the fit of the model to the underlying conditional law of labels given the features vector (Y∣X), e.g. due to model misspecification, over fitting, and high-dimensionality. In this paper, we consider the fundamental problem of assessing the goodness-of-fit for a general binary classifier. Our framework does not make any parametric assumption on the conditional law Y∣X and treats that as a black-box oracle model which can be accessed only through queries. We formulate the goodness-of-fit assessment problem as a tolerance hypothesis testing of the form H0:E[Df(Bern(η(X))‖Bern(η^(X)))]≤τ where Df represents an f-divergence function, and η(x), η^(x), respectively, denote the true and an estimate likelihood for a feature vector x admitting a positive label. We propose a novel test, called Goodness-of-fit with Randomisation and Scoring Procedure (GRASP) for testing H0, which works in finite sample settings, no matter the features (distribution-free). We also propose model-X GRASP designed for model-X settings where the joint distribution of the features vector is known. Model-X GRASP uses this distributional information to achieve better power. We evaluate the performance of our tests through extensive numerical experiments." @default.
- W4386980312 created "2023-09-24" @default.
- W4386980312 creator A5010342958 @default.
- W4386980312 creator A5046669854 @default.
- W4386980312 date "2023-09-23" @default.
- W4386980312 modified "2023-10-18" @default.
- W4386980312 title "GRASP: a goodness-of-fit test for classification learning" @default.
- W4386980312 cites W1484551447 @default.
- W4386980312 cites W1502103205 @default.
- W4386980312 cites W1502338185 @default.
- W4386980312 cites W1970571177 @default.
- W4386980312 cites W1971232747 @default.
- W4386980312 cites W1987719740 @default.
- W4386980312 cites W2031687681 @default.
- W4386980312 cites W2045549211 @default.
- W4386980312 cites W2045803625 @default.
- W4386980312 cites W2049667592 @default.
- W4386980312 cites W2059104151 @default.
- W4386980312 cites W2136885855 @default.
- W4386980312 cites W2166944917 @default.
- W4386980312 cites W2326082135 @default.
- W4386980312 cites W2435554614 @default.
- W4386980312 cites W2602562802 @default.
- W4386980312 cites W2766966154 @default.
- W4386980312 cites W2787894218 @default.
- W4386980312 cites W2963371845 @default.
- W4386980312 cites W2963651028 @default.
- W4386980312 cites W2981798823 @default.
- W4386980312 cites W3005788930 @default.
- W4386980312 cites W3012175154 @default.
- W4386980312 cites W3024697816 @default.
- W4386980312 cites W3043129934 @default.
- W4386980312 cites W3102479286 @default.
- W4386980312 cites W3123447148 @default.
- W4386980312 cites W3175769723 @default.
- W4386980312 cites W4249991467 @default.
- W4386980312 doi "https://doi.org/10.1093/jrsssb/qkad106" @default.
- W4386980312 hasPublicationYear "2023" @default.
- W4386980312 type Work @default.
- W4386980312 citedByCount "0" @default.
- W4386980312 crossrefType "journal-article" @default.
- W4386980312 hasAuthorship W4386980312A5010342958 @default.
- W4386980312 hasAuthorship W4386980312A5046669854 @default.
- W4386980312 hasConcept C105795698 @default.
- W4386980312 hasConcept C111030470 @default.
- W4386980312 hasConcept C117251300 @default.
- W4386980312 hasConcept C119857082 @default.
- W4386980312 hasConcept C132480984 @default.
- W4386980312 hasConcept C153180895 @default.
- W4386980312 hasConcept C154945302 @default.
- W4386980312 hasConcept C171268870 @default.
- W4386980312 hasConcept C199360897 @default.
- W4386980312 hasConcept C33923547 @default.
- W4386980312 hasConcept C41008148 @default.
- W4386980312 hasConcept C82581908 @default.
- W4386980312 hasConcept C87007009 @default.
- W4386980312 hasConcept C95623464 @default.
- W4386980312 hasConceptScore W4386980312C105795698 @default.
- W4386980312 hasConceptScore W4386980312C111030470 @default.
- W4386980312 hasConceptScore W4386980312C117251300 @default.
- W4386980312 hasConceptScore W4386980312C119857082 @default.
- W4386980312 hasConceptScore W4386980312C132480984 @default.
- W4386980312 hasConceptScore W4386980312C153180895 @default.
- W4386980312 hasConceptScore W4386980312C154945302 @default.
- W4386980312 hasConceptScore W4386980312C171268870 @default.
- W4386980312 hasConceptScore W4386980312C199360897 @default.
- W4386980312 hasConceptScore W4386980312C33923547 @default.
- W4386980312 hasConceptScore W4386980312C41008148 @default.
- W4386980312 hasConceptScore W4386980312C82581908 @default.
- W4386980312 hasConceptScore W4386980312C87007009 @default.
- W4386980312 hasConceptScore W4386980312C95623464 @default.
- W4386980312 hasFunder F4320306076 @default.
- W4386980312 hasLocation W43869803121 @default.
- W4386980312 hasOpenAccess W4386980312 @default.
- W4386980312 hasPrimaryLocation W43869803121 @default.
- W4386980312 hasRelatedWork W1582001232 @default.
- W4386980312 hasRelatedWork W1985739971 @default.
- W4386980312 hasRelatedWork W2127561481 @default.
- W4386980312 hasRelatedWork W2563096758 @default.
- W4386980312 hasRelatedWork W258739415 @default.
- W4386980312 hasRelatedWork W2964166909 @default.
- W4386980312 hasRelatedWork W3202615382 @default.
- W4386980312 hasRelatedWork W4233343816 @default.
- W4386980312 hasRelatedWork W4234102824 @default.
- W4386980312 hasRelatedWork W4386053843 @default.
- W4386980312 isParatext "false" @default.
- W4386980312 isRetracted "false" @default.
- W4386980312 workType "article" @default.