Matches in SemOpenAlex for { <https://semopenalex.org/work/W3216279905> ?p ?o ?g. }
Showing items 1 to 90 of
90
with 100 items per page.
- W3216279905 abstract "We present a general methodology for using unlabeled data to design semi supervised learning (SSL) variants of the Empirical Risk Minimization (ERM) learning process. Focusing on generalized linear regression, we analyze of the effectiveness of our SSL approach in improving prediction performance. The key ideas are carefully considering the null model as a competitor, and utilizing the unlabeled data to determine signal-noise combinations where SSL outperforms both supervised learning and the null model. We then use SSL in an adaptive manner based on estimation of the signal and noise. In the special case of linear regression with Gaussian covariates, we prove that the non-adaptive SSL version is in fact not capable of improving on both the supervised estimator and the null model simultaneously, beyond a negligible O(1∕n) term. On the other hand, the adaptive model presented in this work, can achieve a substantial improvement over both competitors simultaneously, under a variety of settings. This is shown empirically through extensive simulations, and extended to other scenarios, such as non-Gaussian covariates, misspecified linear regression, or generalized linear regression with non-linear link functions." @default.
- W3216279905 created "2021-12-06" @default.
- W3216279905 creator A5030080389 @default.
- W3216279905 creator A5039021124 @default.
- W3216279905 date "2022-01-01" @default.
- W3216279905 modified "2023-09-27" @default.
- W3216279905 title "Semi-supervised empirical risk minimization: Using unlabeled data to improve prediction" @default.
- W3216279905 cites W1571801203 @default.
- W3216279905 cites W1965903691 @default.
- W3216279905 cites W1976033737 @default.
- W3216279905 cites W2023832712 @default.
- W3216279905 cites W2052664531 @default.
- W3216279905 cites W2053304222 @default.
- W3216279905 cites W2071176685 @default.
- W3216279905 cites W24859530 @default.
- W3216279905 cites W2581201870 @default.
- W3216279905 cites W2963013132 @default.
- W3216279905 cites W2963566219 @default.
- W3216279905 cites W2964593027 @default.
- W3216279905 cites W4244612695 @default.
- W3216279905 doi "https://doi.org/10.1214/22-ejs1985" @default.
- W3216279905 hasPublicationYear "2022" @default.
- W3216279905 type Work @default.
- W3216279905 sameAs 3216279905 @default.
- W3216279905 citedByCount "0" @default.
- W3216279905 crossrefType "journal-article" @default.
- W3216279905 hasAuthorship W3216279905A5030080389 @default.
- W3216279905 hasAuthorship W3216279905A5039021124 @default.
- W3216279905 hasBestOaLocation W32162799051 @default.
- W3216279905 hasConcept C105795698 @default.
- W3216279905 hasConcept C107321475 @default.
- W3216279905 hasConcept C119043178 @default.
- W3216279905 hasConcept C119857082 @default.
- W3216279905 hasConcept C121332964 @default.
- W3216279905 hasConcept C126255220 @default.
- W3216279905 hasConcept C136389625 @default.
- W3216279905 hasConcept C147764199 @default.
- W3216279905 hasConcept C154945302 @default.
- W3216279905 hasConcept C163175372 @default.
- W3216279905 hasConcept C163716315 @default.
- W3216279905 hasConcept C185429906 @default.
- W3216279905 hasConcept C33923547 @default.
- W3216279905 hasConcept C41008148 @default.
- W3216279905 hasConcept C41587187 @default.
- W3216279905 hasConcept C48921125 @default.
- W3216279905 hasConcept C50644808 @default.
- W3216279905 hasConcept C61326573 @default.
- W3216279905 hasConcept C62520636 @default.
- W3216279905 hasConcept C83546350 @default.
- W3216279905 hasConceptScore W3216279905C105795698 @default.
- W3216279905 hasConceptScore W3216279905C107321475 @default.
- W3216279905 hasConceptScore W3216279905C119043178 @default.
- W3216279905 hasConceptScore W3216279905C119857082 @default.
- W3216279905 hasConceptScore W3216279905C121332964 @default.
- W3216279905 hasConceptScore W3216279905C126255220 @default.
- W3216279905 hasConceptScore W3216279905C136389625 @default.
- W3216279905 hasConceptScore W3216279905C147764199 @default.
- W3216279905 hasConceptScore W3216279905C154945302 @default.
- W3216279905 hasConceptScore W3216279905C163175372 @default.
- W3216279905 hasConceptScore W3216279905C163716315 @default.
- W3216279905 hasConceptScore W3216279905C185429906 @default.
- W3216279905 hasConceptScore W3216279905C33923547 @default.
- W3216279905 hasConceptScore W3216279905C41008148 @default.
- W3216279905 hasConceptScore W3216279905C41587187 @default.
- W3216279905 hasConceptScore W3216279905C48921125 @default.
- W3216279905 hasConceptScore W3216279905C50644808 @default.
- W3216279905 hasConceptScore W3216279905C61326573 @default.
- W3216279905 hasConceptScore W3216279905C62520636 @default.
- W3216279905 hasConceptScore W3216279905C83546350 @default.
- W3216279905 hasIssue "1" @default.
- W3216279905 hasLocation W32162799051 @default.
- W3216279905 hasLocation W32162799052 @default.
- W3216279905 hasLocation W32162799053 @default.
- W3216279905 hasOpenAccess W3216279905 @default.
- W3216279905 hasPrimaryLocation W32162799051 @default.
- W3216279905 hasRelatedWork W1484670700 @default.
- W3216279905 hasRelatedWork W1575939368 @default.
- W3216279905 hasRelatedWork W1591252736 @default.
- W3216279905 hasRelatedWork W2168268496 @default.
- W3216279905 hasRelatedWork W2389250926 @default.
- W3216279905 hasRelatedWork W2498250515 @default.
- W3216279905 hasRelatedWork W3139543054 @default.
- W3216279905 hasRelatedWork W4297040536 @default.
- W3216279905 hasRelatedWork W4310988131 @default.
- W3216279905 hasRelatedWork W4367694085 @default.
- W3216279905 hasVolume "16" @default.
- W3216279905 isParatext "false" @default.
- W3216279905 isRetracted "false" @default.
- W3216279905 magId "3216279905" @default.
- W3216279905 workType "article" @default.