Matches in SemOpenAlex for { <https://semopenalex.org/work/W4285260241> ?p ?o ?g. }
- W4285260241 endingPage "6662" @default.
- W4285260241 startingPage "6631" @default.
- W4285260241 abstract "The recent success of generative adversarial networks and variational learning suggests that training a classification network may work well in addressing the classical two-sample problem, which asks to differentiate two densities given finite samples from each one. Network-based methods have the computational advantage that the algorithm scales to large datasets. This paper considers using the classification logit function, which is provided by a trained classification neural network and evaluated on the testing set split of the two datasets, to compute a two-sample statistic. To analyze the approximation and estimation error of the logit function to differentiate near-manifold densities, we introduce a new result of near-manifold integral approximation by neural networks. We then show that the logit function provably differentiates two sub-exponential densities given that the network is sufficiently parametrized, and for on or near manifold densities, the needed network complexity is reduced to only scale with the intrinsic dimensionality. In experiments, the network logit test demonstrates better performance than previous network-based tests using classification accuracy, and also compares favorably to certain kernel maximum mean discrepancy tests on synthetic datasets and hand-written digit datasets." @default.
- W4285260241 created "2022-07-14" @default.
- W4285260241 creator A5017106522 @default.
- W4285260241 creator A5049178654 @default.
- W4285260241 date "2022-10-01" @default.
- W4285260241 modified "2023-10-10" @default.
- W4285260241 title "Classification Logit Two-Sample Testing by Neural Networks for Differentiating Near Manifold Densities" @default.
- W4285260241 cites W114517082 @default.
- W4285260241 cites W1966026565 @default.
- W4285260241 cites W1972673289 @default.
- W4285260241 cites W2017116866 @default.
- W4285260241 cites W2030150661 @default.
- W4285260241 cites W2079224763 @default.
- W4285260241 cites W2117381306 @default.
- W4285260241 cites W2164943005 @default.
- W4285260241 cites W2233050410 @default.
- W4285260241 cites W2267573953 @default.
- W4285260241 cites W2528305538 @default.
- W4285260241 cites W2886881190 @default.
- W4285260241 cites W2962761333 @default.
- W4285260241 cites W2963095610 @default.
- W4285260241 cites W2963631324 @default.
- W4285260241 cites W2965192329 @default.
- W4285260241 cites W2981407587 @default.
- W4285260241 cites W2994651049 @default.
- W4285260241 cites W3025750359 @default.
- W4285260241 cites W3101996726 @default.
- W4285260241 cites W3108301192 @default.
- W4285260241 cites W3126536233 @default.
- W4285260241 cites W362526619 @default.
- W4285260241 cites W4206923752 @default.
- W4285260241 doi "https://doi.org/10.1109/tit.2022.3175691" @default.
- W4285260241 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/37810208" @default.
- W4285260241 hasPublicationYear "2022" @default.
- W4285260241 type Work @default.
- W4285260241 citedByCount "1" @default.
- W4285260241 countsByYear W42852602412023 @default.
- W4285260241 crossrefType "journal-article" @default.
- W4285260241 hasAuthorship W4285260241A5017106522 @default.
- W4285260241 hasAuthorship W4285260241A5049178654 @default.
- W4285260241 hasBestOaLocation W42852602412 @default.
- W4285260241 hasConcept C111030470 @default.
- W4285260241 hasConcept C11413529 @default.
- W4285260241 hasConcept C114614502 @default.
- W4285260241 hasConcept C119857082 @default.
- W4285260241 hasConcept C126255220 @default.
- W4285260241 hasConcept C140331021 @default.
- W4285260241 hasConcept C14036430 @default.
- W4285260241 hasConcept C153180895 @default.
- W4285260241 hasConcept C154945302 @default.
- W4285260241 hasConcept C185592680 @default.
- W4285260241 hasConcept C198531522 @default.
- W4285260241 hasConcept C33923547 @default.
- W4285260241 hasConcept C41008148 @default.
- W4285260241 hasConcept C43617362 @default.
- W4285260241 hasConcept C50644808 @default.
- W4285260241 hasConcept C74193536 @default.
- W4285260241 hasConcept C78458016 @default.
- W4285260241 hasConcept C86803240 @default.
- W4285260241 hasConcept C91873725 @default.
- W4285260241 hasConceptScore W4285260241C111030470 @default.
- W4285260241 hasConceptScore W4285260241C11413529 @default.
- W4285260241 hasConceptScore W4285260241C114614502 @default.
- W4285260241 hasConceptScore W4285260241C119857082 @default.
- W4285260241 hasConceptScore W4285260241C126255220 @default.
- W4285260241 hasConceptScore W4285260241C140331021 @default.
- W4285260241 hasConceptScore W4285260241C14036430 @default.
- W4285260241 hasConceptScore W4285260241C153180895 @default.
- W4285260241 hasConceptScore W4285260241C154945302 @default.
- W4285260241 hasConceptScore W4285260241C185592680 @default.
- W4285260241 hasConceptScore W4285260241C198531522 @default.
- W4285260241 hasConceptScore W4285260241C33923547 @default.
- W4285260241 hasConceptScore W4285260241C41008148 @default.
- W4285260241 hasConceptScore W4285260241C43617362 @default.
- W4285260241 hasConceptScore W4285260241C50644808 @default.
- W4285260241 hasConceptScore W4285260241C74193536 @default.
- W4285260241 hasConceptScore W4285260241C78458016 @default.
- W4285260241 hasConceptScore W4285260241C86803240 @default.
- W4285260241 hasConceptScore W4285260241C91873725 @default.
- W4285260241 hasFunder F4320306076 @default.
- W4285260241 hasFunder F4320306151 @default.
- W4285260241 hasFunder F4320306819 @default.
- W4285260241 hasFunder F4320332161 @default.
- W4285260241 hasIssue "10" @default.
- W4285260241 hasLocation W42852602411 @default.
- W4285260241 hasLocation W42852602412 @default.
- W4285260241 hasLocation W42852602413 @default.
- W4285260241 hasLocation W42852602414 @default.
- W4285260241 hasOpenAccess W4285260241 @default.
- W4285260241 hasPrimaryLocation W42852602411 @default.
- W4285260241 hasRelatedWork W2355801475 @default.
- W4285260241 hasRelatedWork W2561617217 @default.
- W4285260241 hasRelatedWork W3097449145 @default.
- W4285260241 hasRelatedWork W3113111988 @default.
- W4285260241 hasRelatedWork W3133651710 @default.
- W4285260241 hasRelatedWork W3198417070 @default.
- W4285260241 hasRelatedWork W4287555349 @default.
- W4285260241 hasRelatedWork W4294811468 @default.