A unified framework for high-dimensional analysis of $M$-estimators with decomposable regularizers (Q5965308)

!

This is the item page for this Wikibase entity, intended for internal use and editing purposes. Please use the normal view instead:

A unified framework for high-dimensional analysis of M-estimators with decomposable regularizers

scientific article; zbMATH DE number 6549003

Language	Label	Description	Also known as
default for all languages	No label defined
English	A unified framework for high-dimensional analysis of $M$-estimators with decomposable regularizers	scientific article; zbMATH DE number 6549003

Statements

instance of

scholarly article

0 references

title

A unified framework for high-dimensional analysis of $M$-estimators with decomposable regularizers (English)

0 references

0 references

0 references

0 references

0 references

0 references

3 March 2016

0 references

full work available at URL

https://arxiv.org/abs/1010.2731

0 references

https://projecteuclid.org/euclid.ss/1356098555

0 references

zbMATH Keywords

high-dimensional statistics

0 references

$M$-estimator

0 references

Lasso

0 references

group Lasso

0 references

sparsity

0 references

$\ell_{1}$-regularization

0 references

nuclear norm

0 references

describes a project that uses

PDCO

0 references

hgam

0 references

MaRDI profile type

MaRDI publication profile

0 references

cites work

Estimation of (near) low-rank matrices with noise and high-dimensional scaling

0 references

Self-concordant analysis for logistic regression

0 references

Consistency of the group Lasso and multiple kernel learning

0 references

Consistency of trace norm minimization

0 references

Model-Based Compressive Sensing

0 references

An overview of recent developments in genomics and associated statistical methods

0 references

Covariance regularization by thresholding

0 references

Simultaneous analysis of Lasso and Dantzig selector

0 references

Honest variable selection in linear and logistic regression models via $\ell _{1}$ and $\ell _{1}+\ell _{2}$ penalization

0 references

Sparsity oracle inequalities for the Lasso

0 references

Aggregation for Gaussian regression

0 references

Optimal rates of convergence for covariance matrix estimation

0 references

The Dantzig selector: statistical estimation when $p$ is much larger than $n$. (With discussions and rejoinder).

0 references

Exact matrix completion via convex optimization

0 references

Decoding by Linear Programming

0 references

Rank-Sparsity Incoherence for Matrix Decomposition

0 references

Atomic Decomposition by Basis Pursuit

0 references

Compressed sensing

0 references

Neighborliness of randomly projected simplices in high dimensions

0 references

Operator norm consistent estimation of large-dimensional sparse covariance matrices

0 references

Statistical analysis of observations of increasing dimension. Transl. from the Russian

0 references

Persistene in high-dimensional linear predictor-selection and the virtue of overparametrization

0 references

Robust Matrix Decomposition With Sparse Corruptions

0 references

The benefit of group sparsity

0 references

Proximal methods for hierarchical sparse coding

0 references

Matrix completion from noisy entries

0 references

Blockwise sparse regression

0 references

Sparsity in multiple kernel learning

0 references

Sparsistency and rates of convergence in large covariance matrix estimation

0 references

Interior-point method for nuclear norm approximation with application to system identification

0 references

Oracle inequalities and optimal inference under group sparsity

0 references

Two proposals for robust PCA using semidefinite programming

0 references

Q4001740

0 references

High-dimensional additive modeling

0 references

A note on the Lasso for Gaussian graphical model selection

0 references

High-dimensional graphs and variable selection with the Lasso

0 references

Lasso-type recovery of sparse representations for high-dimensional data

0 references

On the asymptotic properties of the group lasso estimator for linear models

0 references

A unified framework for high-dimensional analysis of $M$-estimators with decomposable regularizers

0 references

Simultaneous Support Recovery in High Dimensions: Benefits and Perils of Block $\ell _{1}/\ell _{\infty} $-Regularization

0 references

Restricted strong convexity and weighted matrix completion: optimal bounds with noise

0 references

Support union recovery in high-dimensional multivariate regression

0 references

Restricted eigenvalue properties for correlated Gaussian designs

0 references

Minimax Rates of Estimation for High-Dimensional Linear Regression Over $\ell_q$-Balls

0 references

Minimax-optimal rates for sparse additive models over kernel classes via convex programming

0 references

High-dimensional Ising model selection using $\ell _{1}$-regularized logistic regression

0 references

High-dimensional covariance estimation by minimizing $\ell _{1}$-penalized log-determinant divergence

0 references

A simpler approach to matrix completion

0 references

Guaranteed minimum-rank solutions of linear matrix equations via nuclear norm minimization

0 references

Estimation of high-dimensional low-rank matrices

0 references

Sparse permutation invariant covariance estimation

0 references

Reconstruction From Anisotropic Random Measurements

0 references

On the Reconstruction of Block-Sparse Signals With an Optimal Number of Measurements

0 references

Q4864293

0 references

Sparsity and Smoothness Via the Fused Lasso

0 references

Algorithms for simultaneous sparse approximation. I: Greedy pursuit

0 references

High-dimensional generalized linear models and the lasso

0 references

On the conditions used to prove oracle results for the Lasso

0 references

Sharp Thresholds for High-Dimensional and Noisy Sparsity Recovery Using $\ell _{1}$-Constrained Quadratic Programming (Lasso)

0 references

Information-Theoretic Limits on Sparsity Recovery in the High-Dimensional and Noisy Setting

0 references

Characteristic vectors of bordered matrices with infinite dimensions

0 references

Robust PCA via Outlier Pursuit

0 references

Model Selection and Estimation in Regression with Grouped Variables

0 references

The sparsity and bias of the LASSO selection in high-dimensional linear regression

0 references

The composite absolute penalties family for grouped and hierarchical variable selection

0 references

Q3174050

0 references

Identifiers

zbMATH Open document ID

1331.62350

0 references

DOI

10.1214/12-STS400

0 references

Mathematics Subject Classification ID

62J07

0 references

zbMATH DE Number

6549003

0 references

Sitelinks

Mathematics(1 entry)

mardi A unified framework for high-dimensional analysis of $M$-estimators with decomposable regularizers

A unified framework for high-dimensional analysis of \(M\)-estimators with decomposable regularizers (Q5965308)

Statements

Identifiers

Sitelinks

Mathematics(1 entry)