Matches in SemOpenAlex for { <https://semopenalex.org/work/W3152160022> ?p ?o ?g. }
Showing items 1 to 77 of
77
with 100 items per page.
- W3152160022 endingPage "864" @default.
- W3152160022 startingPage "850" @default.
- W3152160022 abstract "We give an efficient algorithm for learning a binary function in a given class C of bounded VCdimension, with training data distributed according to P and test data according to Q, where Pand Q may be arbitrary distributions over X. This is the generic form of what is called covariateshift, which is impossible in general as arbitrary P and Q may not even overlap. However, recentlyguarantees were given in a model called PQ-learning (Goldwasser et al., 2020) where the learnerhas: (a) access to unlabeled test examples from Q (in addition to labeled samples from P, i.e.,semi-supervised learning); and (b) the option to reject any example and abstain from classifyingit (i.e., selective classification). The algorithm of Goldwasser et al. (2020) requires an (agnostic)noise-tolerant learner for C. The present work gives a polynomial-time PQ-learning algorithm,called Slice-and-Dice, that uses an oracle to a “reliable” learner for C, where reliable learning(Kalai et al., 2012) is a model of learning with one-sided noise. Furthermore, this reduction isoptimal in the sense that we show the equivalence of reliable and PQ learning." @default.
- W3152160022 created "2021-04-13" @default.
- W3152160022 creator A5065655845 @default.
- W3152160022 creator A5086904495 @default.
- W3152160022 date "2021-01-01" @default.
- W3152160022 modified "2023-09-24" @default.
- W3152160022 title "Efficient learning with arbitrary covariate shift" @default.
- W3152160022 hasPublicationYear "2021" @default.
- W3152160022 type Work @default.
- W3152160022 sameAs 3152160022 @default.
- W3152160022 citedByCount "0" @default.
- W3152160022 crossrefType "proceedings-article" @default.
- W3152160022 hasAuthorship W3152160022A5065655845 @default.
- W3152160022 hasAuthorship W3152160022A5086904495 @default.
- W3152160022 hasConcept C11413529 @default.
- W3152160022 hasConcept C114614502 @default.
- W3152160022 hasConcept C115903868 @default.
- W3152160022 hasConcept C118615104 @default.
- W3152160022 hasConcept C119322782 @default.
- W3152160022 hasConcept C134306372 @default.
- W3152160022 hasConcept C154945302 @default.
- W3152160022 hasConcept C178489894 @default.
- W3152160022 hasConcept C2779014939 @default.
- W3152160022 hasConcept C2780069185 @default.
- W3152160022 hasConcept C311688 @default.
- W3152160022 hasConcept C33676613 @default.
- W3152160022 hasConcept C33923547 @default.
- W3152160022 hasConcept C34388435 @default.
- W3152160022 hasConcept C41008148 @default.
- W3152160022 hasConcept C55166926 @default.
- W3152160022 hasConcept C80444323 @default.
- W3152160022 hasConceptScore W3152160022C11413529 @default.
- W3152160022 hasConceptScore W3152160022C114614502 @default.
- W3152160022 hasConceptScore W3152160022C115903868 @default.
- W3152160022 hasConceptScore W3152160022C118615104 @default.
- W3152160022 hasConceptScore W3152160022C119322782 @default.
- W3152160022 hasConceptScore W3152160022C134306372 @default.
- W3152160022 hasConceptScore W3152160022C154945302 @default.
- W3152160022 hasConceptScore W3152160022C178489894 @default.
- W3152160022 hasConceptScore W3152160022C2779014939 @default.
- W3152160022 hasConceptScore W3152160022C2780069185 @default.
- W3152160022 hasConceptScore W3152160022C311688 @default.
- W3152160022 hasConceptScore W3152160022C33676613 @default.
- W3152160022 hasConceptScore W3152160022C33923547 @default.
- W3152160022 hasConceptScore W3152160022C34388435 @default.
- W3152160022 hasConceptScore W3152160022C41008148 @default.
- W3152160022 hasConceptScore W3152160022C55166926 @default.
- W3152160022 hasConceptScore W3152160022C80444323 @default.
- W3152160022 hasLocation W31521600221 @default.
- W3152160022 hasOpenAccess W3152160022 @default.
- W3152160022 hasPrimaryLocation W31521600221 @default.
- W3152160022 hasRelatedWork W1517526469 @default.
- W3152160022 hasRelatedWork W1547172162 @default.
- W3152160022 hasRelatedWork W1771507533 @default.
- W3152160022 hasRelatedWork W1977696979 @default.
- W3152160022 hasRelatedWork W2014089785 @default.
- W3152160022 hasRelatedWork W2093717447 @default.
- W3152160022 hasRelatedWork W2117756453 @default.
- W3152160022 hasRelatedWork W2149433471 @default.
- W3152160022 hasRelatedWork W2165798027 @default.
- W3152160022 hasRelatedWork W2186076924 @default.
- W3152160022 hasRelatedWork W2201177080 @default.
- W3152160022 hasRelatedWork W254353371 @default.
- W3152160022 hasRelatedWork W2560584392 @default.
- W3152160022 hasRelatedWork W2726793048 @default.
- W3152160022 hasRelatedWork W2914930992 @default.
- W3152160022 hasRelatedWork W3034216758 @default.
- W3152160022 hasRelatedWork W3036841168 @default.
- W3152160022 hasRelatedWork W3041696840 @default.
- W3152160022 hasRelatedWork W3133010718 @default.
- W3152160022 hasRelatedWork W3214102131 @default.
- W3152160022 isParatext "false" @default.
- W3152160022 isRetracted "false" @default.
- W3152160022 magId "3152160022" @default.
- W3152160022 workType "article" @default.