Regularized M|estimators with Nonconvexity

Regularized M-estimators with Nonconvexity: Statistical and ...

Finally, Chen and Gu (2014) showed that specific local optima of nonconvex regularized least-squares problems are stable, so optimization algorithms ini-.

Regularized M-estimators with Nonconvexity: Statistical and ...

Our theory covers many nonconvex objective functions of interest, including the corrected Lasso for errors-in-variables linear models; regression for ...

Regularized M-estimators with nonconvexity: Statistical and ... - NIPS

Abstract. We establish theoretical results concerning all local optima of various regularized M-estimators, where both loss and penalty functions are allowed to ...

Regularized M-estimators with nonconvexity: Statistical and ...

We establish theoretical results concerning local optima of regularized M- estimators, where both loss and penalty functions are allowed to be nonconvex.

Regularized M-estimators with nonconvexity - ACM Digital Library

Our theory covers many nonconvex objective functions of interest, including the corrected Lasso for errors-in-variables linear models; regression for ...

[PDF] Regularized M-estimators with nonconvexity: statistical and ...

Under restricted strong convexity on the loss and suitable regularity conditions on the penalty, it is proved that any stationary point of the composite ...

Regularized M-estimators with nonconvexity - ACM Digital Library

We establish theoretical results concerning local optima of regularized M-estimators, where both loss and penalty functions are allowed to be nonconvex.

Regularized M-estimators With Nonconvexity: Statistical and ...

Download Citation | Regularized M-estimators With Nonconvexity: Statistical and Algorithmic Theory for Local Optima | We establish theoretical results ...

Sparse recovery via nonconvex regularized M-estimators over ℓq-balls

The recovery properties of nonconvex regularized -estimators are analysed, under the general sparsity assumption on the true parameter.

[1911.08061] Sparse recovery via nonconvex regularized $M - arXiv

In the statistical aspect, we establish the recovery bound for any stationary point of the nonconvex regularized M-estimator, under restricted ...

Local Optima of Nonconvex Regularized M-Estimators

More recently, Zhang and Zhang [27] provided statistical guarantees concerning global optima of least-squares linear regression with various.

A case for nonconvex regularization - Project Euclid

M-estimator, Lasso, sparsity, nonconvex regularizer, high-dimensional statistics, variable selection. 2455. Page 2. 2456. P.-L. LOH AND ...

OPTIMAL COMPUTATIONAL AND STATISTICAL RATES OF ... - NCBI

Many important estimators fall in this category, including least squares regression with nonconvex regularization, generalized linear models with nonconvex ...

Robustness and Tractability for Nonconvex M-estimators - NSF PAR

Moreover, we assume p ≫ n and that the true parameter θ0 is sparse. We consider the l1-regularized M-estimator under an l2-constraint on θ: Minimize: θ.

Regularized M-estimators with nonconvexity: Statistical and ... - dblp

Bibliographic details on Regularized M-estimators with nonconvexity: Statistical and algorithmic theory for local optima.

Statistical and algorithmic theory for local optima - Videolectures

We establish theoretical results concerning all local optima of various regularized M-estimators, where both loss and penalty functions are ...

Sparse recovery via nonconvex regularized M-estimators over ℓ_q ...

In the statistical aspect, we establish the recovery bound for any stationary point of the nonconvex regularized M-estimator, under restricted ...

Implicit Regularization in Nonconvex Statistical Estimation: Gradient ...

Here, we assume {\varvec{M}}^{\star } to be positive semidefinite to simplify the presentation, but note that our analysis easily extends to ...

The picasso Package for Nonconvex Regularized M-estimation in ...

An R package named picasso is described, which implements a unified framework of pathwise coordinate optimization for a variety of sparse learning problems, ...

Implicit Regularization in Nonconvex Statistical Estimation

• regularized loss + projection. ◦ e.g. Li, Ling, Strohmer, Wei '16, Huang, Hand '17, Ling, Strohmer. '17. ◦ requires m iterations even with regularization.