FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2949272370> ?p ?o ?g. }

• W2949272370 abstract "Suppose that we observe $y in mathbb{R}^n$ and $X in mathbb{R}^{n times m}$ in the following errors-in-variables model: begin{eqnarray*} y & = & X_0 beta^* +epsilon X & = & X_0 + W, end{eqnarray*} where $X_0$ is an $n times m$ design matrix with independent subgaussian row vectors, $epsilon in mathbb{R}^n$ is a noise vector and $W$ is a mean zero $n times m$ random noise matrix with independent subgaussian column vectors, independent of $X_0$ and $epsilon$. This model is significantly different from those analyzed in the literature in the sense that we allow the measurement error for each covariate to be a dependent vector across its $n$ observations. Such error structures appear in the science literature when modeling the trial-to-trial fluctuations in response strength shared across a set of neurons. Under sparsity and restrictive eigenvalue type of conditions, we show that one is able to recover a sparse vector $beta^* in mathbb{R}^m$ from the model given a single observation matrix $X$ and the response vector $y$. We establish consistency in estimating $beta^*$ and obtain the rates of convergence in the $ell_q$ norm, where $q = 1, 2$. We show error bounds which approach that of the regular Lasso and the Dantzig selector in case the errors in $W$ are tending to 0. We analyze the convergence rates of the gradient descent methods for solving the nonconvex programs and show that the composite gradient descent algorithm is guaranteed to converge at a geometric rate to a neighborhood of the global minimizers: the size of the neighborhood is bounded by the statistical error in the $ell_2$ norm. Our analysis reveals interesting connections between computational and statistical efficiency and the concentration of measure phenomenon in random matrix theory. We provide simulation evidence illuminating the theoretical predictions." @default.
• W2949272370 created "2019-06-27" @default.
• W2949272370 creator A5035089081 @default.
• W2949272370 creator A5057215536 @default.
• W2949272370 date "2016-11-14" @default.
• W2949272370 modified "2023-10-18" @default.
• W2949272370 title "Errors-in-variables models with dependent measurements" @default.
• W2949272370 cites W100695655 @default.
• W2949272370 cites W1498947193 @default.
• W2949272370 cites W1508062313 @default.
• W2949272370 cites W1537097090 @default.
• W2949272370 cites W1656622334 @default.
• W2949272370 cites W1717817085 @default.
• W2949272370 cites W1819101074 @default.
• W2949272370 cites W1972127338 @default.
• W2949272370 cites W1984305442 @default.
• W2949272370 cites W1986931325 @default.
• W2949272370 cites W2006849814 @default.
• W2949272370 cites W2011287710 @default.
• W2949272370 cites W2011622730 @default.
• W2949272370 cites W2022796289 @default.
• W2949272370 cites W2023982864 @default.
• W2949272370 cites W2032267070 @default.
• W2949272370 cites W2032291279 @default.
• W2949272370 cites W2040957501 @default.
• W2949272370 cites W2049633694 @default.
• W2949272370 cites W2057113469 @default.
• W2949272370 cites W2061250208 @default.
• W2949272370 cites W2065145334 @default.
• W2949272370 cites W2074153536 @default.
• W2949272370 cites W2074682976 @default.
• W2949272370 cites W2077813311 @default.
• W2949272370 cites W2078537874 @default.
• W2949272370 cites W2079960018 @default.
• W2949272370 cites W2086439867 @default.
• W2949272370 cites W2090701569 @default.
• W2949272370 cites W2101660706 @default.
• W2949272370 cites W2116148865 @default.
• W2949272370 cites W2119595900 @default.
• W2949272370 cites W2121154640 @default.
• W2949272370 cites W2128453351 @default.
• W2949272370 cites W2129342593 @default.
• W2949272370 cites W2131668296 @default.
• W2949272370 cites W2135046866 @default.
• W2949272370 cites W2152589362 @default.
• W2949272370 cites W2167010377 @default.
• W2949272370 cites W2167864570 @default.
• W2949272370 cites W2566240941 @default.
• W2949272370 cites W2616050959 @default.
• W2949272370 cites W3042168128 @default.
• W2949272370 cites W3098985301 @default.
• W2949272370 cites W3104410610 @default.
• W2949272370 doi "https://doi.org/10.48550/arxiv.1611.04701" @default.
• W2949272370 hasPublicationYear "2016" @default.
• W2949272370 type Work @default.
• W2949272370 sameAs 2949272370 @default.
• W2949272370 citedByCount "0" @default.
• W2949272370 crossrefType "posted-content" @default.
• W2949272370 hasAuthorship W2949272370A5035089081 @default.
• W2949272370 hasAuthorship W2949272370A5057215536 @default.
• W2949272370 hasBestOaLocation W29492723701 @default.
• W2949272370 hasConcept C105795698 @default.
• W2949272370 hasConcept C106487976 @default.
• W2949272370 hasConcept C11413529 @default.
• W2949272370 hasConcept C114614502 @default.
• W2949272370 hasConcept C118615104 @default.
• W2949272370 hasConcept C119857082 @default.
• W2949272370 hasConcept C121332964 @default.
• W2949272370 hasConcept C122123141 @default.
• W2949272370 hasConcept C127162648 @default.
• W2949272370 hasConcept C136764020 @default.
• W2949272370 hasConcept C138405894 @default.
• W2949272370 hasConcept C153258448 @default.
• W2949272370 hasConcept C158693339 @default.
• W2949272370 hasConcept C159985019 @default.
• W2949272370 hasConcept C17744445 @default.
• W2949272370 hasConcept C191795146 @default.
• W2949272370 hasConcept C192562407 @default.
• W2949272370 hasConcept C199539241 @default.
• W2949272370 hasConcept C2776436953 @default.
• W2949272370 hasConcept C28826006 @default.
• W2949272370 hasConcept C2986577269 @default.
• W2949272370 hasConcept C31258907 @default.
• W2949272370 hasConcept C33923547 @default.
• W2949272370 hasConcept C37616216 @default.
• W2949272370 hasConcept C41008148 @default.
• W2949272370 hasConcept C50644808 @default.
• W2949272370 hasConcept C57869625 @default.
• W2949272370 hasConcept C62520636 @default.
• W2949272370 hasConcept C64812099 @default.
• W2949272370 hasConceptScore W2949272370C105795698 @default.
• W2949272370 hasConceptScore W2949272370C106487976 @default.
• W2949272370 hasConceptScore W2949272370C11413529 @default.
• W2949272370 hasConceptScore W2949272370C114614502 @default.
• W2949272370 hasConceptScore W2949272370C118615104 @default.
• W2949272370 hasConceptScore W2949272370C119857082 @default.
• W2949272370 hasConceptScore W2949272370C121332964 @default.
• W2949272370 hasConceptScore W2949272370C122123141 @default.
• W2949272370 hasConceptScore W2949272370C127162648 @default.
• W2949272370 hasConceptScore W2949272370C136764020 @default.

• next