FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W1521672915> ?p ?o ?g. }

• W1521672915 endingPage "81" @default.
• W1521672915 startingPage "73" @default.
• W1521672915 abstract "Recovering a low-rank tensor from incomplete information is a recurring problem in signal processing and machine learning. The most popular convex relaxation of this problem minimizes the sum of the nuclear norms (SNN) of the unfolding matrices of the tensor. We show that this approach can be substantially suboptimal: reliably recovering a K-way n×n×...×n tensor of Tucker rank (r, r,..., r) from Gaussian measurements requires Ω(rnK-1) observations. In contrast, a certain (intractable) nonconvex formulation needs only O(rK+nrK) observations. We introduce a simple, new convex relaxation, which partially bridges this gap. Our new formulation succeeds with O(r⌊K/2⌋n⌈K/2⌉) observations. The lower bound for the SNN model follows from our new result on recovering signals with multiple structures (e.g. sparse, low rank), which indicates the significant suboptimality of the common approach of minimizing the sum of individual sparsity inducing norms (e.g. l1, nuclear norm). Our new tractable formulation for low-rank tensor recovery shows how the sample complexity can be reduced by designing convex regularizers that exploit several structures jointly." @default.
• W1521672915 created "2016-06-24" @default.
• W1521672915 creator A5009495942 @default.
• W1521672915 creator A5019610791 @default.
• W1521672915 creator A5027297328 @default.
• W1521672915 creator A5070028816 @default.
• W1521672915 date "2014-06-21" @default.
• W1521672915 modified "2023-10-03" @default.
• W1521672915 title "Square Deal: Lower Bounds and Improved Relaxations for Tensor Recovery" @default.
• W1521672915 cites W1520871589 @default.
• W1521672915 cites W1546430343 @default.
• W1521672915 cites W1736339626 @default.
• W1521672915 cites W1800334520 @default.
• W1521672915 cites W1921958996 @default.
• W1521672915 cites W1963826206 @default.
• W1521672915 cites W1999136078 @default.
• W1521672915 cites W2024165284 @default.
• W1521672915 cites W2024729328 @default.
• W1521672915 cites W2030628896 @default.
• W1521672915 cites W2078677240 @default.
• W1521672915 cites W2079705627 @default.
• W1521672915 cites W2080843093 @default.
• W1521672915 cites W2091449379 @default.
• W1521672915 cites W2105724942 @default.
• W1521672915 cites W2110355775 @default.
• W1521672915 cites W2118080949 @default.
• W1521672915 cites W2118550318 @default.
• W1521672915 cites W2126256670 @default.
• W1521672915 cites W2130426352 @default.
• W1521672915 cites W2131866613 @default.
• W1521672915 cites W2132639093 @default.
• W1521672915 cites W2137800329 @default.
• W1521672915 cites W2143268884 @default.
• W1521672915 cites W2153496554 @default.
• W1521672915 cites W2164452299 @default.
• W1521672915 cites W2296616510 @default.
• W1521672915 cites W2314222152 @default.
• W1521672915 cites W2963980562 @default.
• W1521672915 cites W60530159 @default.
• W1521672915 cites W905619 @default.
• W1521672915 cites W2740905535 @default.
• W1521672915 hasPublicationYear "2014" @default.
• W1521672915 type Work @default.
• W1521672915 sameAs 1521672915 @default.
• W1521672915 citedByCount "91" @default.
• W1521672915 countsByYear W15216729152013 @default.
• W1521672915 countsByYear W15216729152014 @default.
• W1521672915 countsByYear W15216729152015 @default.
• W1521672915 countsByYear W15216729152016 @default.
• W1521672915 countsByYear W15216729152017 @default.
• W1521672915 countsByYear W15216729152018 @default.
• W1521672915 countsByYear W15216729152019 @default.
• W1521672915 countsByYear W15216729152020 @default.
• W1521672915 countsByYear W15216729152021 @default.
• W1521672915 crossrefType "proceedings-article" @default.
• W1521672915 hasAuthorship W1521672915A5009495942 @default.
• W1521672915 hasAuthorship W1521672915A5019610791 @default.
• W1521672915 hasAuthorship W1521672915A5027297328 @default.
• W1521672915 hasAuthorship W1521672915A5070028816 @default.
• W1521672915 hasConcept C104267543 @default.
• W1521672915 hasConcept C112680207 @default.
• W1521672915 hasConcept C11413529 @default.
• W1521672915 hasConcept C114614502 @default.
• W1521672915 hasConcept C118615104 @default.
• W1521672915 hasConcept C121332964 @default.
• W1521672915 hasConcept C126255220 @default.
• W1521672915 hasConcept C134306372 @default.
• W1521672915 hasConcept C155281189 @default.
• W1521672915 hasConcept C15744967 @default.
• W1521672915 hasConcept C158693339 @default.
• W1521672915 hasConcept C163716315 @default.
• W1521672915 hasConcept C164226766 @default.
• W1521672915 hasConcept C202444582 @default.
• W1521672915 hasConcept C2524010 @default.
• W1521672915 hasConcept C2776029896 @default.
• W1521672915 hasConcept C28826006 @default.
• W1521672915 hasConcept C33923547 @default.
• W1521672915 hasConcept C41008148 @default.
• W1521672915 hasConcept C554190296 @default.
• W1521672915 hasConcept C62520636 @default.
• W1521672915 hasConcept C76155785 @default.
• W1521672915 hasConcept C77553402 @default.
• W1521672915 hasConcept C77805123 @default.
• W1521672915 hasConcept C92207270 @default.
• W1521672915 hasConceptScore W1521672915C104267543 @default.
• W1521672915 hasConceptScore W1521672915C112680207 @default.
• W1521672915 hasConceptScore W1521672915C11413529 @default.
• W1521672915 hasConceptScore W1521672915C114614502 @default.
• W1521672915 hasConceptScore W1521672915C118615104 @default.
• W1521672915 hasConceptScore W1521672915C121332964 @default.
• W1521672915 hasConceptScore W1521672915C126255220 @default.
• W1521672915 hasConceptScore W1521672915C134306372 @default.
• W1521672915 hasConceptScore W1521672915C155281189 @default.
• W1521672915 hasConceptScore W1521672915C15744967 @default.
• W1521672915 hasConceptScore W1521672915C158693339 @default.
• W1521672915 hasConceptScore W1521672915C163716315 @default.
• W1521672915 hasConceptScore W1521672915C164226766 @default.
• W1521672915 hasConceptScore W1521672915C202444582 @default.

• next