• Aucun résultat trouvé

[PDF] Top 20 Sparse Regularization on Thin Grids I: the LASSO

Has 10000 "Sparse Regularization on Thin Grids I: the LASSO" found on our website. Below are the top 20 most common "Sparse Regularization on Thin Grids I: the LASSO".

Sparse Regularization on Thin Grids I: the LASSO

Sparse Regularization on Thin Grids I: the LASSO

... study the behavior of the method for inverse problems regularization when the discretization step size tends to ...that the sought after sparse sum of Diracs is recovered when ... Voir le document complet

30

Sparse Spikes Super-resolution on Thin Grids II: the Continuous Basis Pursuit

Sparse Spikes Super-resolution on Thin Grids II: the Continuous Basis Pursuit

... how the C-BP is able to reach sub-grid accuracy in favorable situation, outperforming the ...on the typical grids used by ...on the grid size, but also on the complexity of ... Voir le document complet

47

Generalized Concomitant Multi-Task Lasso for Sparse Multimodal Regression

Generalized Concomitant Multi-Task Lasso for Sparse Multimodal Regression

... ]. The so-called M/EEG inverse problem, which consists in identifying active brain regions, can be cast as a high-dimensional sparse regression ...of the limited number of sensors, as well as ... Voir le document complet

11

Wasserstein regularization for sparse multi-task regression

Wasserstein regularization for sparse multi-task regression

... leverage the spatial information associ- ated to regressors. Indeed, while sparse priors enforce that only a small subset of variables is used, the assumption that these regressors overlap across all ... Voir le document complet

16

Learning Sparse Neural Networks via Sensitivity-Driven Regularization

Learning Sparse Neural Networks via Sensitivity-Driven Regularization

... work Sparse neural architectures have been the focus of intense research recently due the advantages they ...large sparse architecture improves the network generalization ability in a ... Voir le document complet

12

l1-spectral clustering algorithm: a robust spectral clustering using Lasso regularization

l1-spectral clustering algorithm: a robust spectral clustering using Lasso regularization

... to the k-means algorithm, which is highly sensitive to ...of the k-means to noisy settings so that it recovers the cluster structure in spite of the unstructured part of the input data ... Voir le document complet

24

Group Lasso with Overlaps: the Latent Group Lasso approach

Group Lasso with Overlaps: the Latent Group Lasso approach

... group Lasso, sparsity, graph, support recovery, block regularization, feature selection ...recently. Sparse models are attractive in many application domains because they lend themselves particularly ... Voir le document complet

61

A Dynamic Screening Principle for the Lasso

A Dynamic Screening Principle for the Lasso

... upon the SAFE sphere, e.g. the dome test [13], they can combine into a dynamic screening ...strategy. The proposed method raises several questions we plan to work on, some of them are addressed here ... Voir le document complet

6

Improving thin structures in surface reconstruction from sparse point cloud

Improving thin structures in surface reconstruction from sparse point cloud

... in the classifications above. In [1], the input point cloud is first approximated by planar segments, then these segments are prolonged and assembled into a well-behaved surface using visibility ... Voir le document complet

17

Dynamic Screening: Accelerating First-Order Algorithms for the Lasso and Group-Lasso

Dynamic Screening: Accelerating First-Order Algorithms for the Lasso and Group-Lasso

... algorithms, the dynamic strategy shows a significant acceleration in a wide range of parameter λ ≥ ...of the running time and 80% of the number of flops. The static strategy is efficient in a ... Voir le document complet

20

An l1-Oracle Inequality for the Lasso

An l1-Oracle Inequality for the Lasso

... by the Lasso and deduce rates of convergence of this estimator whenever the target function belongs to some interpolation space between L 1 ( D) and the Hilbert space H = R n ...that ... Voir le document complet

53

SPOQ lp-Over-lq Regularization for Sparse Signal Recovery applied to Mass Spectrometry

SPOQ lp-Over-lq Regularization for Sparse Signal Recovery applied to Mass Spectrometry

... I. I NTRODUCTION AND BACKGROUND A. On the role of sparsity measures in data science The law of parsimony (or Occam’s razor 1 ) is an important heuristic principle and a guideline in history, ... Voir le document complet

14

Des lapons sans lasso

Des lapons sans lasso

... CNRS UPR34 Résumé Chez les pasteurs de Kautokeino (nord de la Norvège), le marquage des faons par découpe des oreilles constitue l'un des moments cruciaux du cycle annuel de l'élevage du renne. Il se pratique ... Voir le document complet

19

Bayesian sparse regularization for parallel MRI reconstruction using Complex Bernoulli-Laplace mixture priors

Bayesian sparse regularization for parallel MRI reconstruction using Complex Bernoulli-Laplace mixture priors

... along the phase encoding direction, which gener- ally leads to a sampling below the Nyquist rate ...[2]. The measured reduced FoV images present aliasing ar- tifacts in the image domain after ... Voir le document complet

9

Bayesian sparse regularization for parallel MRI reconstruction using Complex Bernoulli-Laplace mixture priors

Bayesian sparse regularization for parallel MRI reconstruction using Complex Bernoulli-Laplace mixture priors

... in the original space two sparsity levels of the desired image without using any ...here the same model as in ...of the whole model is ...fields. The paper is structured as follows. In ... Voir le document complet

10

Transductive versions of the LASSO and the Dantzig Selector

Transductive versions of the LASSO and the Dantzig Selector

... methods, the identification of the true support {j : β ∗ j 6= 0} of the vector β ∗ is also in ...that the estimator ˆ β and the true vector β ∗ share the same support at least ... Voir le document complet

25

Improved Local Spectral Unmixing of hyperspectral data using an algorithmic regularization path for collaborative sparse regression

Improved Local Spectral Unmixing of hyperspectral data using an algorithmic regularization path for collaborative sparse regression

... with the proposed region model. We show the effect of collaborative sparsity on the local number of endmembers, in ...using the BIC criterion on the sequence of models extracted by ... Voir le document complet

6

The group fused Lasso for multiple change-point detection

The group fused Lasso for multiple change-point detection

... Finding the place (or time) where most or all of a set of one-dimensional signals (or profiles) jointly change in some specific way is an important question in several ...patients. The latter application is ... Voir le document complet

25

On the oriented chromatic number of grids

On the oriented chromatic number of grids

... L’archive ouverte pluridisciplinaire HAL, est destinée au dépôt et à la diffusion de documents scientifiques de niveau recherche, publiés ou non, émanant des établissements d’enseignemen[r] ... Voir le document complet

9

On the Dynamic Resources Availability in Grids

On the Dynamic Resources Availability in Grids

... We further model four aspects of grid resource availability: the time when resource failures occur, the duration of a failure, the number of nodes affected by a failure, and the distribu[r] ... Voir le document complet

26

Show all 10000 documents...