Matches in SemOpenAlex for { <https://semopenalex.org/work/W4317802040> ?p ?o ?g. }
Showing items 1 to 85 of
85
with 100 items per page.
- W4317802040 endingPage "109356" @default.
- W4317802040 startingPage "109356" @default.
- W4317802040 abstract "Vector-valued learning, where the output space admits a vector-valued structure, is an important problem that covers a broad family of important domains, e.g. multi-task learning and transfer learning. Using local Rademacher complexity and unlabeled data, we derive novel semi-supervised excess risk bounds for general vector-valued learning from both kernel perspective and linear perspective. The derived bounds are much sharper than existing ones and the convergence rates are improved from the square root of labeled sample size to the square root of total sample size or directly dependent on labeled sample size. Motivated by our theoretical analysis, we propose a general semi-supervised algorithm for efficiently learning vector-valued functions, incorporating both local Rademacher complexity and Laplacian regularization. Extensive experimental results illustrate the proposed algorithm significantly outperforms the compared methods, which coincides with our theoretical findings." @default.
- W4317802040 created "2023-01-24" @default.
- W4317802040 creator A5015477789 @default.
- W4317802040 creator A5023783253 @default.
- W4317802040 creator A5077114895 @default.
- W4317802040 date "2023-06-01" @default.
- W4317802040 modified "2023-09-27" @default.
- W4317802040 title "Semi-supervised vector-valued learning: Improved bounds and algorithms" @default.
- W4317802040 cites W1794760533 @default.
- W4317802040 cites W1992530282 @default.
- W4317802040 cites W2090630554 @default.
- W4317802040 cites W2102443333 @default.
- W4317802040 cites W2159680539 @default.
- W4317802040 cites W2172000360 @default.
- W4317802040 cites W2472087060 @default.
- W4317802040 cites W2905371339 @default.
- W4317802040 cites W2962937842 @default.
- W4317802040 cites W2963973173 @default.
- W4317802040 cites W3080683114 @default.
- W4317802040 cites W3100743579 @default.
- W4317802040 cites W3133128010 @default.
- W4317802040 cites W3170031697 @default.
- W4317802040 cites W3205749498 @default.
- W4317802040 cites W4283080368 @default.
- W4317802040 doi "https://doi.org/10.1016/j.patcog.2023.109356" @default.
- W4317802040 hasPublicationYear "2023" @default.
- W4317802040 type Work @default.
- W4317802040 citedByCount "0" @default.
- W4317802040 crossrefType "journal-article" @default.
- W4317802040 hasAuthorship W4317802040A5015477789 @default.
- W4317802040 hasAuthorship W4317802040A5023783253 @default.
- W4317802040 hasAuthorship W4317802040A5077114895 @default.
- W4317802040 hasBestOaLocation W43178020402 @default.
- W4317802040 hasConcept C11413529 @default.
- W4317802040 hasConcept C11577676 @default.
- W4317802040 hasConcept C118615104 @default.
- W4317802040 hasConcept C122280245 @default.
- W4317802040 hasConcept C12267149 @default.
- W4317802040 hasConcept C12713177 @default.
- W4317802040 hasConcept C136389625 @default.
- W4317802040 hasConcept C154945302 @default.
- W4317802040 hasConcept C2524010 @default.
- W4317802040 hasConcept C2776135515 @default.
- W4317802040 hasConcept C33923547 @default.
- W4317802040 hasConcept C41008148 @default.
- W4317802040 hasConcept C50644808 @default.
- W4317802040 hasConcept C58973888 @default.
- W4317802040 hasConcept C74193536 @default.
- W4317802040 hasConceptScore W4317802040C11413529 @default.
- W4317802040 hasConceptScore W4317802040C11577676 @default.
- W4317802040 hasConceptScore W4317802040C118615104 @default.
- W4317802040 hasConceptScore W4317802040C122280245 @default.
- W4317802040 hasConceptScore W4317802040C12267149 @default.
- W4317802040 hasConceptScore W4317802040C12713177 @default.
- W4317802040 hasConceptScore W4317802040C136389625 @default.
- W4317802040 hasConceptScore W4317802040C154945302 @default.
- W4317802040 hasConceptScore W4317802040C2524010 @default.
- W4317802040 hasConceptScore W4317802040C2776135515 @default.
- W4317802040 hasConceptScore W4317802040C33923547 @default.
- W4317802040 hasConceptScore W4317802040C41008148 @default.
- W4317802040 hasConceptScore W4317802040C50644808 @default.
- W4317802040 hasConceptScore W4317802040C58973888 @default.
- W4317802040 hasConceptScore W4317802040C74193536 @default.
- W4317802040 hasFunder F4320321001 @default.
- W4317802040 hasFunder F4320322919 @default.
- W4317802040 hasLocation W43178020401 @default.
- W4317802040 hasLocation W43178020402 @default.
- W4317802040 hasOpenAccess W4317802040 @default.
- W4317802040 hasPrimaryLocation W43178020401 @default.
- W4317802040 hasRelatedWork W1539287799 @default.
- W4317802040 hasRelatedWork W2098217755 @default.
- W4317802040 hasRelatedWork W2108697353 @default.
- W4317802040 hasRelatedWork W2119156797 @default.
- W4317802040 hasRelatedWork W2127615859 @default.
- W4317802040 hasRelatedWork W2137362393 @default.
- W4317802040 hasRelatedWork W2169565408 @default.
- W4317802040 hasRelatedWork W2361876834 @default.
- W4317802040 hasRelatedWork W2399572917 @default.
- W4317802040 hasRelatedWork W3004569186 @default.
- W4317802040 hasVolume "138" @default.
- W4317802040 isParatext "false" @default.
- W4317802040 isRetracted "false" @default.
- W4317802040 workType "article" @default.