Matches in SemOpenAlex for { <https://semopenalex.org/work/W771491333> ?p ?o ?g. }
Showing items 1 to 95 of
95
with 100 items per page.
- W771491333 abstract "Recently theoretical guarantees have been obtained for matrix completion in the non-uniform sampling regime. In particular, if the sampling distribution aligns with the underlying matrix's leverage scores, then with high probability nuclear norm minimization will exactly recover the low rank matrix. In this article, we analyze the scenario in which the non-uniform sampling distribution may or may not not align with the underlying matrix's leverage scores. Here we explore learning the parameters for weighted nuclear norm minimization in terms of the empirical sampling distribution. We provide a sufficiency condition for these learned weights which provide an exact recovery guarantee for weighted nuclear norm minimization. It has been established that a specific choice of weights in terms of the true sampling distribution not only allows for weighted nuclear norm minimization to exactly recover the low rank matrix, but also allows for a quantifiable relaxation in the exact recovery conditions. In this article we extend this quantifiable relaxation in exact recovery conditions for a specific choice of weights defined analogously in terms of the empirical distribution as opposed to the true sampling distribution. To accomplish this we employ a concentration of measure bound and a large deviation bound. We also present numerical evidence for the healthy robustness of the weighted nuclear norm minimization algorithm to the choice of empirically learned weights. These numerical experiments show that for a variety of easily computable empirical weights, weighted nuclear norm minimization outperforms unweighted nuclear norm minimization in the non-uniform sampling regime." @default.
- W771491333 created "2016-06-24" @default.
- W771491333 creator A5061978177 @default.
- W771491333 date "2014-12-31" @default.
- W771491333 modified "2023-09-27" @default.
- W771491333 title "Learning Parameters for Weighted Matrix Completion via Empirical Estimation" @default.
- W771491333 cites W1653728640 @default.
- W771491333 cites W1736339626 @default.
- W771491333 cites W2103012681 @default.
- W771491333 cites W2103972604 @default.
- W771491333 cites W2111297856 @default.
- W771491333 cites W2118550318 @default.
- W771491333 cites W2120872934 @default.
- W771491333 cites W2124608575 @default.
- W771491333 cites W2134332047 @default.
- W771491333 cites W2144730813 @default.
- W771491333 hasPublicationYear "2014" @default.
- W771491333 type Work @default.
- W771491333 sameAs 771491333 @default.
- W771491333 citedByCount "0" @default.
- W771491333 crossrefType "posted-content" @default.
- W771491333 hasAuthorship W771491333A5061978177 @default.
- W771491333 hasConcept C105795698 @default.
- W771491333 hasConcept C106487976 @default.
- W771491333 hasConcept C107321475 @default.
- W771491333 hasConcept C121332964 @default.
- W771491333 hasConcept C126255220 @default.
- W771491333 hasConcept C147764199 @default.
- W771491333 hasConcept C153083717 @default.
- W771491333 hasConcept C155281189 @default.
- W771491333 hasConcept C158693339 @default.
- W771491333 hasConcept C159985019 @default.
- W771491333 hasConcept C163716315 @default.
- W771491333 hasConcept C17744445 @default.
- W771491333 hasConcept C191795146 @default.
- W771491333 hasConcept C192562407 @default.
- W771491333 hasConcept C199539241 @default.
- W771491333 hasConcept C202444582 @default.
- W771491333 hasConcept C2778459887 @default.
- W771491333 hasConcept C28826006 @default.
- W771491333 hasConcept C33923547 @default.
- W771491333 hasConcept C41008148 @default.
- W771491333 hasConcept C62520636 @default.
- W771491333 hasConcept C90199385 @default.
- W771491333 hasConcept C92207270 @default.
- W771491333 hasConceptScore W771491333C105795698 @default.
- W771491333 hasConceptScore W771491333C106487976 @default.
- W771491333 hasConceptScore W771491333C107321475 @default.
- W771491333 hasConceptScore W771491333C121332964 @default.
- W771491333 hasConceptScore W771491333C126255220 @default.
- W771491333 hasConceptScore W771491333C147764199 @default.
- W771491333 hasConceptScore W771491333C153083717 @default.
- W771491333 hasConceptScore W771491333C155281189 @default.
- W771491333 hasConceptScore W771491333C158693339 @default.
- W771491333 hasConceptScore W771491333C159985019 @default.
- W771491333 hasConceptScore W771491333C163716315 @default.
- W771491333 hasConceptScore W771491333C17744445 @default.
- W771491333 hasConceptScore W771491333C191795146 @default.
- W771491333 hasConceptScore W771491333C192562407 @default.
- W771491333 hasConceptScore W771491333C199539241 @default.
- W771491333 hasConceptScore W771491333C202444582 @default.
- W771491333 hasConceptScore W771491333C2778459887 @default.
- W771491333 hasConceptScore W771491333C28826006 @default.
- W771491333 hasConceptScore W771491333C33923547 @default.
- W771491333 hasConceptScore W771491333C41008148 @default.
- W771491333 hasConceptScore W771491333C62520636 @default.
- W771491333 hasConceptScore W771491333C90199385 @default.
- W771491333 hasConceptScore W771491333C92207270 @default.
- W771491333 hasLocation W7714913331 @default.
- W771491333 hasOpenAccess W771491333 @default.
- W771491333 hasPrimaryLocation W7714913331 @default.
- W771491333 hasRelatedWork W1806401590 @default.
- W771491333 hasRelatedWork W2001303579 @default.
- W771491333 hasRelatedWork W2037668862 @default.
- W771491333 hasRelatedWork W2098812560 @default.
- W771491333 hasRelatedWork W2109357635 @default.
- W771491333 hasRelatedWork W2115722836 @default.
- W771491333 hasRelatedWork W2244549531 @default.
- W771491333 hasRelatedWork W2536820994 @default.
- W771491333 hasRelatedWork W2884785844 @default.
- W771491333 hasRelatedWork W2914330359 @default.
- W771491333 hasRelatedWork W2938943746 @default.
- W771491333 hasRelatedWork W2952418124 @default.
- W771491333 hasRelatedWork W2962829336 @default.
- W771491333 hasRelatedWork W2963834123 @default.
- W771491333 hasRelatedWork W3035079661 @default.
- W771491333 hasRelatedWork W3125671026 @default.
- W771491333 hasRelatedWork W3173832989 @default.
- W771491333 hasRelatedWork W3193748961 @default.
- W771491333 hasRelatedWork W3193804560 @default.
- W771491333 hasRelatedWork W3101237976 @default.
- W771491333 isParatext "false" @default.
- W771491333 isRetracted "false" @default.
- W771491333 magId "771491333" @default.
- W771491333 workType "article" @default.