Matches in SemOpenAlex for { <https://semopenalex.org/work/W2952767562> ?p ?o ?g. }
- W2952767562 abstract "Regularization is a well recognized powerful strategy to improve the performance of a learning machine and $l^q$ regularization schemes with $0<q<infty$ are central in use. It is known that different $q$ leads to different properties of the deduced estimators, say, $l^2$ regularization leads to smooth estimators while $l^1$ regularization leads to sparse estimators. Then, how does the generalization capabilities of $l^q$ regularization learning vary with $q$? In this paper, we study this problem in the framework of statistical learning theory and show that implementing $l^q$ coefficient regularization schemes in the sample dependent hypothesis space associated with Gaussian kernel can attain the same almost optimal learning rates for all $0<q<infty$. That is, the upper and lower bounds of learning rates for $l^q$ regularization learning are asymptotically identical for all $0<q<infty$. Our finding tentatively reveals that, in some modeling contexts, the choice of $q$ might not have a strong impact with respect to the generalization capability. From this perspective, $q$ can be arbitrarily specified, or specified merely by other no generalization criteria like smoothness, computational complexity, sparsity, etc.." @default.
- W2952767562 created "2019-06-27" @default.
- W2952767562 creator A5022287632 @default.
- W2952767562 creator A5028936141 @default.
- W2952767562 creator A5064967477 @default.
- W2952767562 creator A5075938156 @default.
- W2952767562 date "2013-12-19" @default.
- W2952767562 modified "2023-10-15" @default.
- W2952767562 title "Learning rates of $l^q$ coefficient regularization learning with Gaussian kernel" @default.
- W2952767562 cites W1480376833 @default.
- W2952767562 cites W1484867920 @default.
- W2952767562 cites W1560724230 @default.
- W2952767562 cites W1572999479 @default.
- W2952767562 cites W1698155719 @default.
- W2952767562 cites W1943431218 @default.
- W2952767562 cites W194417083 @default.
- W2952767562 cites W1963616278 @default.
- W2952767562 cites W1968436459 @default.
- W2952767562 cites W1979384859 @default.
- W2952767562 cites W1993288992 @default.
- W2952767562 cites W1994642189 @default.
- W2952767562 cites W1996388931 @default.
- W2952767562 cites W2012501405 @default.
- W2952767562 cites W2016865000 @default.
- W2952767562 cites W2017332415 @default.
- W2952767562 cites W2040468026 @default.
- W2952767562 cites W2047278710 @default.
- W2952767562 cites W2056201402 @default.
- W2952767562 cites W2062024414 @default.
- W2952767562 cites W2076126353 @default.
- W2952767562 cites W2079223539 @default.
- W2952767562 cites W2097581423 @default.
- W2952767562 cites W2110456244 @default.
- W2952767562 cites W2115706991 @default.
- W2952767562 cites W2119883478 @default.
- W2952767562 cites W2125085449 @default.
- W2952767562 cites W2135046866 @default.
- W2952767562 cites W2140348539 @default.
- W2952767562 cites W2154558852 @default.
- W2952767562 cites W2952108874 @default.
- W2952767562 cites W3103790796 @default.
- W2952767562 cites W3106361977 @default.
- W2952767562 cites W597932189 @default.
- W2952767562 doi "https://doi.org/10.48550/arxiv.1312.5465" @default.
- W2952767562 hasPublicationYear "2013" @default.
- W2952767562 type Work @default.
- W2952767562 sameAs 2952767562 @default.
- W2952767562 citedByCount "0" @default.
- W2952767562 crossrefType "posted-content" @default.
- W2952767562 hasAuthorship W2952767562A5022287632 @default.
- W2952767562 hasAuthorship W2952767562A5028936141 @default.
- W2952767562 hasAuthorship W2952767562A5064967477 @default.
- W2952767562 hasAuthorship W2952767562A5075938156 @default.
- W2952767562 hasBestOaLocation W29527675621 @default.
- W2952767562 hasConcept C105795698 @default.
- W2952767562 hasConcept C121332964 @default.
- W2952767562 hasConcept C126255220 @default.
- W2952767562 hasConcept C134306372 @default.
- W2952767562 hasConcept C135252773 @default.
- W2952767562 hasConcept C141718189 @default.
- W2952767562 hasConcept C152442038 @default.
- W2952767562 hasConcept C154945302 @default.
- W2952767562 hasConcept C163716315 @default.
- W2952767562 hasConcept C185429906 @default.
- W2952767562 hasConcept C2776135515 @default.
- W2952767562 hasConcept C28826006 @default.
- W2952767562 hasConcept C33923547 @default.
- W2952767562 hasConcept C41008148 @default.
- W2952767562 hasConcept C62520636 @default.
- W2952767562 hasConceptScore W2952767562C105795698 @default.
- W2952767562 hasConceptScore W2952767562C121332964 @default.
- W2952767562 hasConceptScore W2952767562C126255220 @default.
- W2952767562 hasConceptScore W2952767562C134306372 @default.
- W2952767562 hasConceptScore W2952767562C135252773 @default.
- W2952767562 hasConceptScore W2952767562C141718189 @default.
- W2952767562 hasConceptScore W2952767562C152442038 @default.
- W2952767562 hasConceptScore W2952767562C154945302 @default.
- W2952767562 hasConceptScore W2952767562C163716315 @default.
- W2952767562 hasConceptScore W2952767562C185429906 @default.
- W2952767562 hasConceptScore W2952767562C2776135515 @default.
- W2952767562 hasConceptScore W2952767562C28826006 @default.
- W2952767562 hasConceptScore W2952767562C33923547 @default.
- W2952767562 hasConceptScore W2952767562C41008148 @default.
- W2952767562 hasConceptScore W2952767562C62520636 @default.
- W2952767562 hasLocation W29527675621 @default.
- W2952767562 hasOpenAccess W2952767562 @default.
- W2952767562 hasPrimaryLocation W29527675621 @default.
- W2952767562 hasRelatedWork W1570628932 @default.
- W2952767562 hasRelatedWork W1989857057 @default.
- W2952767562 hasRelatedWork W2062975788 @default.
- W2952767562 hasRelatedWork W2127592563 @default.
- W2952767562 hasRelatedWork W2196847968 @default.
- W2952767562 hasRelatedWork W2366023887 @default.
- W2952767562 hasRelatedWork W2388364587 @default.
- W2952767562 hasRelatedWork W2935233291 @default.
- W2952767562 hasRelatedWork W3110578843 @default.
- W2952767562 hasRelatedWork W4205464645 @default.
- W2952767562 isParatext "false" @default.
- W2952767562 isRetracted "false" @default.
- W2952767562 magId "2952767562" @default.