Matches in SemOpenAlex for { <https://semopenalex.org/work/W2790875733> ?p ?o ?g. }
- W2790875733 abstract "In this paper, the goal is to reconstruct a tensor, i.e., a multi-dimensional array, when only subsets of its entries are observed. For well-posedness, the tensor is assumed to have a low-Tucker-rank structure. To estimate the underlying tensor from its partial observations, we first propose an estimator based on a newly defined balanced spectral $(k,p)$ -support norm. To efficiently compute the estimator, we come up with a scalable algorithm for the minimization of the spectral $(k,p)$ -support norm. Instead of directly solving the primal problem which involves full SVD in each iteration, the proposed algorithm benefits from the Lagrangian dual through minimizing the dual norm of the $(k,p)$ -support norm which only computes the first $k$ leading singular values and singular vectors in each iteration. To explore the statistical performance of the proposed estimator, upper bounds on the sample complexity and estimation error are then established. Simulation studies confirm that the error bounds can predict the scalable behavior of the estimation error. Experimental results on synthetic and real datasets demonstrate that the spectral $(k,p)$ -support norm based method outperforms the nuclear norm based ones." @default.
- W2790875733 created "2018-03-29" @default.
- W2790875733 creator A5016813986 @default.
- W2790875733 creator A5034883264 @default.
- W2790875733 creator A5054332012 @default.
- W2790875733 creator A5056168495 @default.
- W2790875733 date "2018-01-01" @default.
- W2790875733 modified "2023-10-17" @default.
- W2790875733 title "Tensor Completion Using Spectral $(k,p)$ -Support Norm" @default.
- W2790875733 cites W1521672915 @default.
- W2790875733 cites W1547968147 @default.
- W2790875733 cites W1638985343 @default.
- W2790875733 cites W1963826206 @default.
- W2790875733 cites W1999136078 @default.
- W2790875733 cites W2024165284 @default.
- W2790875733 cites W2029213856 @default.
- W2790875733 cites W2030628896 @default.
- W2790875733 cites W2030927653 @default.
- W2790875733 cites W2079705627 @default.
- W2790875733 cites W2087425408 @default.
- W2790875733 cites W2091449379 @default.
- W2790875733 cites W2103537693 @default.
- W2790875733 cites W2106904876 @default.
- W2790875733 cites W2118080949 @default.
- W2790875733 cites W2118550318 @default.
- W2790875733 cites W2119412403 @default.
- W2790875733 cites W2121739212 @default.
- W2790875733 cites W2147512299 @default.
- W2790875733 cites W2152273324 @default.
- W2790875733 cites W2164278908 @default.
- W2790875733 cites W2185924058 @default.
- W2790875733 cites W2268674159 @default.
- W2790875733 cites W2431890537 @default.
- W2790875733 cites W2469230926 @default.
- W2790875733 cites W2516041031 @default.
- W2790875733 cites W2528907418 @default.
- W2790875733 cites W2539067236 @default.
- W2790875733 cites W2552259797 @default.
- W2790875733 cites W2767962166 @default.
- W2790875733 cites W2775406537 @default.
- W2790875733 cites W2963112220 @default.
- W2790875733 cites W2963328634 @default.
- W2790875733 cites W2963472624 @default.
- W2790875733 cites W2963705450 @default.
- W2790875733 cites W2963852766 @default.
- W2790875733 cites W2963980562 @default.
- W2790875733 cites W3098807808 @default.
- W2790875733 cites W850425088 @default.
- W2790875733 doi "https://doi.org/10.1109/access.2018.2811396" @default.
- W2790875733 hasPublicationYear "2018" @default.
- W2790875733 type Work @default.
- W2790875733 sameAs 2790875733 @default.
- W2790875733 citedByCount "8" @default.
- W2790875733 countsByYear W27908757332018 @default.
- W2790875733 countsByYear W27908757332019 @default.
- W2790875733 crossrefType "journal-article" @default.
- W2790875733 hasAuthorship W2790875733A5016813986 @default.
- W2790875733 hasAuthorship W2790875733A5034883264 @default.
- W2790875733 hasAuthorship W2790875733A5054332012 @default.
- W2790875733 hasAuthorship W2790875733A5056168495 @default.
- W2790875733 hasBestOaLocation W27908757331 @default.
- W2790875733 hasConcept C105795698 @default.
- W2790875733 hasConcept C11413529 @default.
- W2790875733 hasConcept C121332964 @default.
- W2790875733 hasConcept C126255220 @default.
- W2790875733 hasConcept C155281189 @default.
- W2790875733 hasConcept C158693339 @default.
- W2790875733 hasConcept C17744445 @default.
- W2790875733 hasConcept C185429906 @default.
- W2790875733 hasConcept C191795146 @default.
- W2790875733 hasConcept C199539241 @default.
- W2790875733 hasConcept C202444582 @default.
- W2790875733 hasConcept C22789450 @default.
- W2790875733 hasConcept C28826006 @default.
- W2790875733 hasConcept C33923547 @default.
- W2790875733 hasConcept C41008148 @default.
- W2790875733 hasConcept C62520636 @default.
- W2790875733 hasConcept C92207270 @default.
- W2790875733 hasConceptScore W2790875733C105795698 @default.
- W2790875733 hasConceptScore W2790875733C11413529 @default.
- W2790875733 hasConceptScore W2790875733C121332964 @default.
- W2790875733 hasConceptScore W2790875733C126255220 @default.
- W2790875733 hasConceptScore W2790875733C155281189 @default.
- W2790875733 hasConceptScore W2790875733C158693339 @default.
- W2790875733 hasConceptScore W2790875733C17744445 @default.
- W2790875733 hasConceptScore W2790875733C185429906 @default.
- W2790875733 hasConceptScore W2790875733C191795146 @default.
- W2790875733 hasConceptScore W2790875733C199539241 @default.
- W2790875733 hasConceptScore W2790875733C202444582 @default.
- W2790875733 hasConceptScore W2790875733C22789450 @default.
- W2790875733 hasConceptScore W2790875733C28826006 @default.
- W2790875733 hasConceptScore W2790875733C33923547 @default.
- W2790875733 hasConceptScore W2790875733C41008148 @default.
- W2790875733 hasConceptScore W2790875733C62520636 @default.
- W2790875733 hasConceptScore W2790875733C92207270 @default.
- W2790875733 hasFunder F4320321001 @default.
- W2790875733 hasLocation W27908757331 @default.
- W2790875733 hasOpenAccess W2790875733 @default.
- W2790875733 hasPrimaryLocation W27908757331 @default.
- W2790875733 hasRelatedWork W1994537880 @default.