Matches in SemOpenAlex for { <https://semopenalex.org/work/W2918249320> ?p ?o ?g. }
Showing items 1 to 78 of
78
with 100 items per page.
- W2918249320 endingPage "4202" @default.
- W2918249320 startingPage "4193" @default.
- W2918249320 abstract "We study the interplay between surrogate methods for structured prediction and techniques from multitask learning designed to leverage relationships between surrogate outputs. We propose an efficient algorithm based on trace norm regularization which, differently from previous methods, does not require explicit knowledge of the coding/decoding functions of the surrogate framework. As a result, our algorithm can be applied to the broad class of problems in which the surrogate space is large or even infinite dimensional. We study excess risk bounds for trace norm regularized structured prediction, implying the consistency and learning rates for our estimator. We also identify relevant regimes in which our approach can enjoy better generalization performance than previous methods. Numerical experiments on ranking problems indicate that enforcing low-rank relations among surrogate outputs may indeed provide a significant advantage in practice." @default.
- W2918249320 created "2019-03-11" @default.
- W2918249320 creator A5000582003 @default.
- W2918249320 creator A5030913426 @default.
- W2918249320 creator A5034260726 @default.
- W2918249320 creator A5048960946 @default.
- W2918249320 date "2019-05-24" @default.
- W2918249320 modified "2023-09-24" @default.
- W2918249320 title "Leveraging Low-Rank Relations Between Surrogate Tasks in Structured Prediction" @default.
- W2918249320 hasPublicationYear "2019" @default.
- W2918249320 type Work @default.
- W2918249320 sameAs 2918249320 @default.
- W2918249320 citedByCount "3" @default.
- W2918249320 countsByYear W29182493202019 @default.
- W2918249320 countsByYear W29182493202020 @default.
- W2918249320 countsByYear W29182493202021 @default.
- W2918249320 crossrefType "proceedings-article" @default.
- W2918249320 hasAuthorship W2918249320A5000582003 @default.
- W2918249320 hasAuthorship W2918249320A5030913426 @default.
- W2918249320 hasAuthorship W2918249320A5034260726 @default.
- W2918249320 hasAuthorship W2918249320A5048960946 @default.
- W2918249320 hasConcept C105795698 @default.
- W2918249320 hasConcept C11413529 @default.
- W2918249320 hasConcept C119857082 @default.
- W2918249320 hasConcept C126255220 @default.
- W2918249320 hasConcept C153083717 @default.
- W2918249320 hasConcept C154945302 @default.
- W2918249320 hasConcept C185429906 @default.
- W2918249320 hasConcept C189430467 @default.
- W2918249320 hasConcept C2776135515 @default.
- W2918249320 hasConcept C33923547 @default.
- W2918249320 hasConcept C41008148 @default.
- W2918249320 hasConcept C57273362 @default.
- W2918249320 hasConcept C80444323 @default.
- W2918249320 hasConcept C86037889 @default.
- W2918249320 hasConceptScore W2918249320C105795698 @default.
- W2918249320 hasConceptScore W2918249320C11413529 @default.
- W2918249320 hasConceptScore W2918249320C119857082 @default.
- W2918249320 hasConceptScore W2918249320C126255220 @default.
- W2918249320 hasConceptScore W2918249320C153083717 @default.
- W2918249320 hasConceptScore W2918249320C154945302 @default.
- W2918249320 hasConceptScore W2918249320C185429906 @default.
- W2918249320 hasConceptScore W2918249320C189430467 @default.
- W2918249320 hasConceptScore W2918249320C2776135515 @default.
- W2918249320 hasConceptScore W2918249320C33923547 @default.
- W2918249320 hasConceptScore W2918249320C41008148 @default.
- W2918249320 hasConceptScore W2918249320C57273362 @default.
- W2918249320 hasConceptScore W2918249320C80444323 @default.
- W2918249320 hasConceptScore W2918249320C86037889 @default.
- W2918249320 hasLocation W29182493201 @default.
- W2918249320 hasOpenAccess W2918249320 @default.
- W2918249320 hasPrimaryLocation W29182493201 @default.
- W2918249320 hasRelatedWork W132240252 @default.
- W2918249320 hasRelatedWork W2191710671 @default.
- W2918249320 hasRelatedWork W2358113125 @default.
- W2918249320 hasRelatedWork W2726321600 @default.
- W2918249320 hasRelatedWork W2787551658 @default.
- W2918249320 hasRelatedWork W2936176764 @default.
- W2918249320 hasRelatedWork W2947731685 @default.
- W2918249320 hasRelatedWork W2949750828 @default.
- W2918249320 hasRelatedWork W2950515451 @default.
- W2918249320 hasRelatedWork W2952237318 @default.
- W2918249320 hasRelatedWork W2953188617 @default.
- W2918249320 hasRelatedWork W2962909570 @default.
- W2918249320 hasRelatedWork W2969999938 @default.
- W2918249320 hasRelatedWork W2979757782 @default.
- W2918249320 hasRelatedWork W2980725178 @default.
- W2918249320 hasRelatedWork W3100556893 @default.
- W2918249320 hasRelatedWork W3105997200 @default.
- W2918249320 hasRelatedWork W3157050624 @default.
- W2918249320 hasRelatedWork W3189058335 @default.
- W2918249320 hasRelatedWork W3208832035 @default.
- W2918249320 isParatext "false" @default.
- W2918249320 isRetracted "false" @default.
- W2918249320 magId "2918249320" @default.
- W2918249320 workType "article" @default.