Matches in SemOpenAlex for { <https://semopenalex.org/work/W2803374080> ?p ?o ?g. }
Showing items 1 to 88 of
88
with 100 items per page.
- W2803374080 abstract "In this paper, we recover sparse signals from their noisy linear measurements by solving nonlinear differential inclusions, which is based on the notion of inverse scale space (ISS) developed in applied mathematics. Our goal here is to bring this idea to address a challenging problem in statistics, emph{i.e.} finding the oracle estimator which is unbiased and sign-consistent using dynamics. We call our dynamics emph{Bregman ISS} and emph{Linearized Bregman ISS}. A well-known shortcoming of LASSO and any convex regularization approaches lies in the bias of estimators. However, we show that under proper conditions, there exists a bias-free and sign-consistent point on the solution paths of such dynamics, which corresponds to a signal that is the unbiased estimate of the true signal and whose entries have the same signs as those of the true signs, emph{i.e.} the oracle estimator. Therefore, their solution paths are regularization paths better than the LASSO regularization path, since the points on the latter path are biased when sign-consistency is reached. We also show how to efficiently compute their solution paths in both continuous and discretized settings: the full solution paths can be exactly computed piece by piece, and a discretization leads to emph{Linearized Bregman iteration}, which is a simple iterative thresholding rule and easy to parallelize. Theoretical guarantees such as sign-consistency and minimax optimal $l_2$-error bounds are established in both continuous and discrete settings for specific points on the paths. Early-stopping rules for identifying these points are given. The key treatment relies on the development of differential inequalities for differential inclusions and their discretizations, which extends the previous results and leads to exponentially fast recovering of sparse signals before selecting wrong ones." @default.
- W2803374080 created "2018-06-01" @default.
- W2803374080 creator A5002037883 @default.
- W2803374080 creator A5018743231 @default.
- W2803374080 creator A5027720794 @default.
- W2803374080 creator A5051299066 @default.
- W2803374080 creator A5085908411 @default.
- W2803374080 date "2014-06-30" @default.
- W2803374080 modified "2023-09-24" @default.
- W2803374080 title "Noisy Sparsity Recovery via Differential Equations" @default.
- W2803374080 hasPublicationYear "2014" @default.
- W2803374080 type Work @default.
- W2803374080 sameAs 2803374080 @default.
- W2803374080 citedByCount "1" @default.
- W2803374080 countsByYear W28033740802014 @default.
- W2803374080 crossrefType "posted-content" @default.
- W2803374080 hasAuthorship W2803374080A5002037883 @default.
- W2803374080 hasAuthorship W2803374080A5018743231 @default.
- W2803374080 hasAuthorship W2803374080A5027720794 @default.
- W2803374080 hasAuthorship W2803374080A5051299066 @default.
- W2803374080 hasAuthorship W2803374080A5085908411 @default.
- W2803374080 hasConcept C105795698 @default.
- W2803374080 hasConcept C11413529 @default.
- W2803374080 hasConcept C121332964 @default.
- W2803374080 hasConcept C126255220 @default.
- W2803374080 hasConcept C134306372 @default.
- W2803374080 hasConcept C136764020 @default.
- W2803374080 hasConcept C149728462 @default.
- W2803374080 hasConcept C154945302 @default.
- W2803374080 hasConcept C158622935 @default.
- W2803374080 hasConcept C185429906 @default.
- W2803374080 hasConcept C199360897 @default.
- W2803374080 hasConcept C22324862 @default.
- W2803374080 hasConcept C2776135515 @default.
- W2803374080 hasConcept C2777735758 @default.
- W2803374080 hasConcept C28826006 @default.
- W2803374080 hasConcept C33923547 @default.
- W2803374080 hasConcept C37616216 @default.
- W2803374080 hasConcept C41008148 @default.
- W2803374080 hasConcept C62520636 @default.
- W2803374080 hasConcept C73000952 @default.
- W2803374080 hasConceptScore W2803374080C105795698 @default.
- W2803374080 hasConceptScore W2803374080C11413529 @default.
- W2803374080 hasConceptScore W2803374080C121332964 @default.
- W2803374080 hasConceptScore W2803374080C126255220 @default.
- W2803374080 hasConceptScore W2803374080C134306372 @default.
- W2803374080 hasConceptScore W2803374080C136764020 @default.
- W2803374080 hasConceptScore W2803374080C149728462 @default.
- W2803374080 hasConceptScore W2803374080C154945302 @default.
- W2803374080 hasConceptScore W2803374080C158622935 @default.
- W2803374080 hasConceptScore W2803374080C185429906 @default.
- W2803374080 hasConceptScore W2803374080C199360897 @default.
- W2803374080 hasConceptScore W2803374080C22324862 @default.
- W2803374080 hasConceptScore W2803374080C2776135515 @default.
- W2803374080 hasConceptScore W2803374080C2777735758 @default.
- W2803374080 hasConceptScore W2803374080C28826006 @default.
- W2803374080 hasConceptScore W2803374080C33923547 @default.
- W2803374080 hasConceptScore W2803374080C37616216 @default.
- W2803374080 hasConceptScore W2803374080C41008148 @default.
- W2803374080 hasConceptScore W2803374080C62520636 @default.
- W2803374080 hasConceptScore W2803374080C73000952 @default.
- W2803374080 hasLocation W28033740801 @default.
- W2803374080 hasOpenAccess W2803374080 @default.
- W2803374080 hasPrimaryLocation W28033740801 @default.
- W2803374080 hasRelatedWork W1562941967 @default.
- W2803374080 hasRelatedWork W1689484996 @default.
- W2803374080 hasRelatedWork W2160035703 @default.
- W2803374080 hasRelatedWork W2188295559 @default.
- W2803374080 hasRelatedWork W2285154971 @default.
- W2803374080 hasRelatedWork W2528532538 @default.
- W2803374080 hasRelatedWork W2561976564 @default.
- W2803374080 hasRelatedWork W2664571037 @default.
- W2803374080 hasRelatedWork W2798824195 @default.
- W2803374080 hasRelatedWork W289002709 @default.
- W2803374080 hasRelatedWork W2910526316 @default.
- W2803374080 hasRelatedWork W2964256664 @default.
- W2803374080 hasRelatedWork W2966273422 @default.
- W2803374080 hasRelatedWork W2970170116 @default.
- W2803374080 hasRelatedWork W3037347970 @default.
- W2803374080 hasRelatedWork W3103820806 @default.
- W2803374080 hasRelatedWork W3126471803 @default.
- W2803374080 hasRelatedWork W3134155979 @default.
- W2803374080 hasRelatedWork W3209502942 @default.
- W2803374080 hasRelatedWork W3213994367 @default.
- W2803374080 isParatext "false" @default.
- W2803374080 isRetracted "false" @default.
- W2803374080 magId "2803374080" @default.
- W2803374080 workType "article" @default.