Matches in SemOpenAlex for { <https://semopenalex.org/work/W3213019012> ?p ?o ?g. }
- W3213019012 abstract "We study sparse linear regression over a network of agents, modeled as an undirected graph (with no centralized node). The estimation problem is formulated as the minimization of the sum of the local LASSO loss functions plus a quadratic penalty of the consensus constraint -- the latter being instrumental to obtain distributed solution methods. While penalty-based consensus methods have been extensively studied in the optimization literature, their statistical and computational guarantees in the high dimensional setting remain unclear. This work provides an answer to this open problem. Our contribution is two-fold. First, we establish statistical consistency of the estimator: under a suitable choice of the penalty parameter, the optimal solution of the penalized problem achieves near optimal minimax rate $mathcal{O}(s log d/N)$ in $ell_2$-loss, where $s$ is the sparsity value, $d$ is the ambient dimension, and $N$ is the total sample size in the network -- this matches centralized sample rates. Second, we show that the proximal-gradient algorithm applied to the penalized problem, which naturally leads to distributed implementations, converges linearly up to a tolerance of the order of the centralized statistical error -- the rate scales as $mathcal{O}(d)$, revealing an unavoidable speed-accuracy dilemma.Numerical results demonstrate the tightness of the derived sample rate and convergence rate scalings." @default.
- W3213019012 created "2021-11-22" @default.
- W3213019012 creator A5035701991 @default.
- W3213019012 creator A5041765559 @default.
- W3213019012 creator A5046695536 @default.
- W3213019012 creator A5070127492 @default.
- W3213019012 date "2021-11-11" @default.
- W3213019012 modified "2023-09-26" @default.
- W3213019012 title "Distributed Sparse Regression via Penalization" @default.
- W3213019012 cites W1523985187 @default.
- W3213019012 cites W1571416372 @default.
- W3213019012 cites W1616857247 @default.
- W3213019012 cites W1627780903 @default.
- W3213019012 cites W1978259121 @default.
- W3213019012 cites W2009702064 @default.
- W3213019012 cites W2012445782 @default.
- W3213019012 cites W2029080014 @default.
- W3213019012 cites W2030644468 @default.
- W3213019012 cites W2039050532 @default.
- W3213019012 cites W2044212084 @default.
- W3213019012 cites W2057873962 @default.
- W3213019012 cites W2068357778 @default.
- W3213019012 cites W2093417350 @default.
- W3213019012 cites W2100556411 @default.
- W3213019012 cites W2114791779 @default.
- W3213019012 cites W2123705108 @default.
- W3213019012 cites W2129122308 @default.
- W3213019012 cites W2129638195 @default.
- W3213019012 cites W2135046866 @default.
- W3213019012 cites W2142682063 @default.
- W3213019012 cites W2146482778 @default.
- W3213019012 cites W2146842127 @default.
- W3213019012 cites W2151685478 @default.
- W3213019012 cites W2159700154 @default.
- W3213019012 cites W2162312215 @default.
- W3213019012 cites W2266148951 @default.
- W3213019012 cites W2566240941 @default.
- W3213019012 cites W2737743075 @default.
- W3213019012 cites W2782375002 @default.
- W3213019012 cites W2902228345 @default.
- W3213019012 cites W2912099989 @default.
- W3213019012 cites W2962771678 @default.
- W3213019012 cites W2963118312 @default.
- W3213019012 cites W2963254198 @default.
- W3213019012 cites W2963649943 @default.
- W3213019012 cites W2964026281 @default.
- W3213019012 cites W2964256184 @default.
- W3213019012 cites W2965497096 @default.
- W3213019012 cites W3042491641 @default.
- W3213019012 cites W3092262213 @default.
- W3213019012 cites W3093673559 @default.
- W3213019012 cites W3100513551 @default.
- W3213019012 cites W3101710822 @default.
- W3213019012 doi "https://doi.org/10.48550/arxiv.2111.06530" @default.
- W3213019012 hasPublicationYear "2021" @default.
- W3213019012 type Work @default.
- W3213019012 sameAs 3213019012 @default.
- W3213019012 citedByCount "0" @default.
- W3213019012 crossrefType "posted-content" @default.
- W3213019012 hasAuthorship W3213019012A5035701991 @default.
- W3213019012 hasAuthorship W3213019012A5041765559 @default.
- W3213019012 hasAuthorship W3213019012A5046695536 @default.
- W3213019012 hasAuthorship W3213019012A5070127492 @default.
- W3213019012 hasBestOaLocation W32130190121 @default.
- W3213019012 hasConcept C105795698 @default.
- W3213019012 hasConcept C11413529 @default.
- W3213019012 hasConcept C114614502 @default.
- W3213019012 hasConcept C126255220 @default.
- W3213019012 hasConcept C127162648 @default.
- W3213019012 hasConcept C129844170 @default.
- W3213019012 hasConcept C136764020 @default.
- W3213019012 hasConcept C149728462 @default.
- W3213019012 hasConcept C162324750 @default.
- W3213019012 hasConcept C185429906 @default.
- W3213019012 hasConcept C2524010 @default.
- W3213019012 hasConcept C2777303404 @default.
- W3213019012 hasConcept C28826006 @default.
- W3213019012 hasConcept C31258907 @default.
- W3213019012 hasConcept C33676613 @default.
- W3213019012 hasConcept C33923547 @default.
- W3213019012 hasConcept C37616216 @default.
- W3213019012 hasConcept C41008148 @default.
- W3213019012 hasConcept C50522688 @default.
- W3213019012 hasConcept C57869625 @default.
- W3213019012 hasConcept C6180225 @default.
- W3213019012 hasConceptScore W3213019012C105795698 @default.
- W3213019012 hasConceptScore W3213019012C11413529 @default.
- W3213019012 hasConceptScore W3213019012C114614502 @default.
- W3213019012 hasConceptScore W3213019012C126255220 @default.
- W3213019012 hasConceptScore W3213019012C127162648 @default.
- W3213019012 hasConceptScore W3213019012C129844170 @default.
- W3213019012 hasConceptScore W3213019012C136764020 @default.
- W3213019012 hasConceptScore W3213019012C149728462 @default.
- W3213019012 hasConceptScore W3213019012C162324750 @default.
- W3213019012 hasConceptScore W3213019012C185429906 @default.
- W3213019012 hasConceptScore W3213019012C2524010 @default.
- W3213019012 hasConceptScore W3213019012C2777303404 @default.
- W3213019012 hasConceptScore W3213019012C28826006 @default.
- W3213019012 hasConceptScore W3213019012C31258907 @default.
- W3213019012 hasConceptScore W3213019012C33676613 @default.