Matches in SemOpenAlex for { <https://semopenalex.org/work/W2097079088> ?p ?o ?g. }
Showing items 1 to 94 of
94
with 100 items per page.
- W2097079088 abstract "In supervised learning, we commonly assume that training and test data are sampled from the same distribution. However, this assumption can be violated in practice and then standard machine learning techniques perform poorly. This paper focuses on revealing and improving the performance of Bayesian estimation when the training and test distributions are different. We formally analyze the asymptotic Bayesian generalization error and establish its upper bound under a very general setting. Our important finding is that lower order terms---which can be ignored in the absence of the distribution change---play an important role under the distribution change. We also propose a novel variant of stochastic complexity which can be used for choosing an appropriate model and hyper-parameters under a particular distribution change." @default.
- W2097079088 created "2016-06-24" @default.
- W2097079088 creator A5004328317 @default.
- W2097079088 creator A5015169524 @default.
- W2097079088 creator A5072744508 @default.
- W2097079088 creator A5072994165 @default.
- W2097079088 creator A5089768991 @default.
- W2097079088 date "2007-01-01" @default.
- W2097079088 modified "2023-10-03" @default.
- W2097079088 title "Asymptotic Bayesian generalization error when training and test distributions are different" @default.
- W2097079088 cites W1498183065 @default.
- W2097079088 cites W1594725708 @default.
- W2097079088 cites W1607624180 @default.
- W2097079088 cites W189742998 @default.
- W2097079088 cites W1963661053 @default.
- W2097079088 cites W1968908999 @default.
- W2097079088 cites W2017137572 @default.
- W2097079088 cites W2033976720 @default.
- W2097079088 cites W2034368206 @default.
- W2097079088 cites W2081850149 @default.
- W2097079088 cites W2106006415 @default.
- W2097079088 cites W2112081648 @default.
- W2097079088 cites W2112483442 @default.
- W2097079088 cites W2114338449 @default.
- W2097079088 cites W2120217353 @default.
- W2097079088 cites W2133370198 @default.
- W2097079088 cites W2139122730 @default.
- W2097079088 cites W2142635246 @default.
- W2097079088 cites W2144578442 @default.
- W2097079088 cites W2168175751 @default.
- W2097079088 cites W2255883267 @default.
- W2097079088 cites W2811380766 @default.
- W2097079088 cites W3023786531 @default.
- W2097079088 doi "https://doi.org/10.1145/1273496.1273632" @default.
- W2097079088 hasPublicationYear "2007" @default.
- W2097079088 type Work @default.
- W2097079088 sameAs 2097079088 @default.
- W2097079088 citedByCount "24" @default.
- W2097079088 countsByYear W20970790882012 @default.
- W2097079088 countsByYear W20970790882015 @default.
- W2097079088 countsByYear W20970790882017 @default.
- W2097079088 countsByYear W20970790882018 @default.
- W2097079088 countsByYear W20970790882019 @default.
- W2097079088 countsByYear W20970790882020 @default.
- W2097079088 countsByYear W20970790882021 @default.
- W2097079088 countsByYear W20970790882022 @default.
- W2097079088 countsByYear W20970790882023 @default.
- W2097079088 crossrefType "proceedings-article" @default.
- W2097079088 hasAuthorship W2097079088A5004328317 @default.
- W2097079088 hasAuthorship W2097079088A5015169524 @default.
- W2097079088 hasAuthorship W2097079088A5072744508 @default.
- W2097079088 hasAuthorship W2097079088A5072994165 @default.
- W2097079088 hasAuthorship W2097079088A5089768991 @default.
- W2097079088 hasConcept C107673813 @default.
- W2097079088 hasConcept C110121322 @default.
- W2097079088 hasConcept C112972136 @default.
- W2097079088 hasConcept C11413529 @default.
- W2097079088 hasConcept C117765406 @default.
- W2097079088 hasConcept C119857082 @default.
- W2097079088 hasConcept C134306372 @default.
- W2097079088 hasConcept C154945302 @default.
- W2097079088 hasConcept C177148314 @default.
- W2097079088 hasConcept C177769412 @default.
- W2097079088 hasConcept C33923547 @default.
- W2097079088 hasConcept C41008148 @default.
- W2097079088 hasConceptScore W2097079088C107673813 @default.
- W2097079088 hasConceptScore W2097079088C110121322 @default.
- W2097079088 hasConceptScore W2097079088C112972136 @default.
- W2097079088 hasConceptScore W2097079088C11413529 @default.
- W2097079088 hasConceptScore W2097079088C117765406 @default.
- W2097079088 hasConceptScore W2097079088C119857082 @default.
- W2097079088 hasConceptScore W2097079088C134306372 @default.
- W2097079088 hasConceptScore W2097079088C154945302 @default.
- W2097079088 hasConceptScore W2097079088C177148314 @default.
- W2097079088 hasConceptScore W2097079088C177769412 @default.
- W2097079088 hasConceptScore W2097079088C33923547 @default.
- W2097079088 hasConceptScore W2097079088C41008148 @default.
- W2097079088 hasLocation W20970790881 @default.
- W2097079088 hasOpenAccess W2097079088 @default.
- W2097079088 hasPrimaryLocation W20970790881 @default.
- W2097079088 hasRelatedWork W2246260811 @default.
- W2097079088 hasRelatedWork W2361785652 @default.
- W2097079088 hasRelatedWork W2363419996 @default.
- W2097079088 hasRelatedWork W2461164881 @default.
- W2097079088 hasRelatedWork W2607567015 @default.
- W2097079088 hasRelatedWork W2898882859 @default.
- W2097079088 hasRelatedWork W2965483395 @default.
- W2097079088 hasRelatedWork W2989932438 @default.
- W2097079088 hasRelatedWork W4205140086 @default.
- W2097079088 hasRelatedWork W96862169 @default.
- W2097079088 isParatext "false" @default.
- W2097079088 isRetracted "false" @default.
- W2097079088 magId "2097079088" @default.
- W2097079088 workType "article" @default.