FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2938943746> ?p ?o ?g. }

• W2938943746 abstract "A growing number of modern statistical learning problems involve estimating a large number of parameters from a (smaller) number of noisy observations. In a subset of these problems (matrix completion, matrix compressed sensing, and multi-task learning) the unknown parameters form a high-dimensional matrix B*, and two popular approaches for the estimation are convex relaxation of rank-penalized regression or non-convex optimization. It is also known that these estimators satisfy near optimal error bounds under assumptions on rank, coherence, or spikiness of the unknown matrix. In this paper, we introduce a unifying technique for analyzing all of these problems via both estimators that leads to short proofs for the existing results as well as new results. Specifically, first we introduce a general notion of spikiness for B* and consider a general family of estimators and prove non-asymptotic error bounds for the their estimation error. Our approach relies on a generic recipe to prove restricted strong convexity for the sampling operator of the trace regression. Second, and most notably, we prove similar error bounds when the regularization parameter is chosen via K-fold cross-validation. This result is significant in that existing theory on cross-validated estimators do not apply to our setting since our estimators are not known to satisfy their required notion of stability. Third, we study applications of our general results to four subproblems of (1) matrix completion, (2) multi-task learning, (3) compressed sensing with Gaussian ensembles, and (4) compressed sensing with factored measurements. For (1), (3), and (4) we recover matching error bounds as those found in the literature, and for (2) we obtain (to the best of our knowledge) the first such error bound. We also demonstrate how our frameworks applies to the exact recovery problem in (3) and (4)." @default.
• W2938943746 created "2019-04-25" @default.
• W2938943746 creator A5048079293 @default.
• W2938943746 creator A5091599934 @default.
• W2938943746 date "2019-04-18" @default.
• W2938943746 modified "2023-09-27" @default.
• W2938943746 title "On Low-rank Trace Regression under General Sampling Distribution." @default.
• W2938943746 cites W1498282191 @default.
• W2938943746 cites W1523985187 @default.
• W2938943746 cites W1546851689 @default.
• W2938943746 cites W1863732927 @default.
• W2938943746 cites W2047071281 @default.
• W2938943746 cites W2111297856 @default.
• W2938943746 cites W2114892327 @default.
• W2938943746 cites W2118550318 @default.
• W2938943746 cites W2120872934 @default.
• W2938943746 cites W2124608575 @default.
• W2938943746 cites W2134332047 @default.
• W2938943746 cites W2146130798 @default.
• W2938943746 cites W2152836620 @default.
• W2938943746 cites W2162451874 @default.
• W2938943746 cites W2268674159 @default.
• W2938943746 cites W2586353914 @default.
• W2938943746 cites W2616032753 @default.
• W2938943746 cites W2698058871 @default.
• W2938943746 cites W2913340405 @default.
• W2938943746 cites W2962769133 @default.
• W2938943746 cites W2964300712 @default.
• W2938943746 cites W2965497096 @default.
• W2938943746 cites W3004727828 @default.
• W2938943746 cites W3098494111 @default.
• W2938943746 cites W3098807808 @default.
• W2938943746 cites W811143457 @default.
• W2938943746 cites W2144730813 @default.
• W2938943746 hasPublicationYear "2019" @default.
• W2938943746 type Work @default.
• W2938943746 sameAs 2938943746 @default.
• W2938943746 citedByCount "3" @default.
• W2938943746 countsByYear W29389437462018 @default.
• W2938943746 countsByYear W29389437462021 @default.
• W2938943746 crossrefType "posted-content" @default.
• W2938943746 hasAuthorship W2938943746A5048079293 @default.
• W2938943746 hasAuthorship W2938943746A5091599934 @default.
• W2938943746 hasConcept C105795698 @default.
• W2938943746 hasConcept C106131492 @default.
• W2938943746 hasConcept C106487976 @default.
• W2938943746 hasConcept C112680207 @default.
• W2938943746 hasConcept C11413529 @default.
• W2938943746 hasConcept C114614502 @default.
• W2938943746 hasConcept C121332964 @default.
• W2938943746 hasConcept C124851039 @default.
• W2938943746 hasConcept C126255220 @default.
• W2938943746 hasConcept C138885662 @default.
• W2938943746 hasConcept C140779682 @default.
• W2938943746 hasConcept C154945302 @default.
• W2938943746 hasConcept C157972887 @default.
• W2938943746 hasConcept C159985019 @default.
• W2938943746 hasConcept C163716315 @default.
• W2938943746 hasConcept C164226766 @default.
• W2938943746 hasConcept C185429906 @default.
• W2938943746 hasConcept C192562407 @default.
• W2938943746 hasConcept C2524010 @default.
• W2938943746 hasConcept C2776135515 @default.
• W2938943746 hasConcept C2778459887 @default.
• W2938943746 hasConcept C28826006 @default.
• W2938943746 hasConcept C31972630 @default.
• W2938943746 hasConcept C33923547 @default.
• W2938943746 hasConcept C41008148 @default.
• W2938943746 hasConcept C41895202 @default.
• W2938943746 hasConcept C62520636 @default.
• W2938943746 hasConcept C75291252 @default.
• W2938943746 hasConceptScore W2938943746C105795698 @default.
• W2938943746 hasConceptScore W2938943746C106131492 @default.
• W2938943746 hasConceptScore W2938943746C106487976 @default.
• W2938943746 hasConceptScore W2938943746C112680207 @default.
• W2938943746 hasConceptScore W2938943746C11413529 @default.
• W2938943746 hasConceptScore W2938943746C114614502 @default.
• W2938943746 hasConceptScore W2938943746C121332964 @default.
• W2938943746 hasConceptScore W2938943746C124851039 @default.
• W2938943746 hasConceptScore W2938943746C126255220 @default.
• W2938943746 hasConceptScore W2938943746C138885662 @default.
• W2938943746 hasConceptScore W2938943746C140779682 @default.
• W2938943746 hasConceptScore W2938943746C154945302 @default.
• W2938943746 hasConceptScore W2938943746C157972887 @default.
• W2938943746 hasConceptScore W2938943746C159985019 @default.
• W2938943746 hasConceptScore W2938943746C163716315 @default.
• W2938943746 hasConceptScore W2938943746C164226766 @default.
• W2938943746 hasConceptScore W2938943746C185429906 @default.
• W2938943746 hasConceptScore W2938943746C192562407 @default.
• W2938943746 hasConceptScore W2938943746C2524010 @default.
• W2938943746 hasConceptScore W2938943746C2776135515 @default.
• W2938943746 hasConceptScore W2938943746C2778459887 @default.
• W2938943746 hasConceptScore W2938943746C28826006 @default.
• W2938943746 hasConceptScore W2938943746C31972630 @default.
• W2938943746 hasConceptScore W2938943746C33923547 @default.
• W2938943746 hasConceptScore W2938943746C41008148 @default.
• W2938943746 hasConceptScore W2938943746C41895202 @default.
• W2938943746 hasConceptScore W2938943746C62520636 @default.
• W2938943746 hasConceptScore W2938943746C75291252 @default.
• W2938943746 hasLocation W29389437461 @default.

• next