Sharp Oracle Inequalities for Square Root Regularization

zbMath1441.62188arXiv1509.04093MaRDI QIDQ4636972

Benjamin Stucky, Sara van de Geer

Publication date: 17 April 2018

Full work available at URL: https://arxiv.org/abs/1509.04093

zbMATH Keywords

structured sparsityKarush-Kuhn-Tuckersquare root Lassoweak decomposabilitysharp oracale inequality

Mathematics Subject Classification ID

Ridge regression; shrinkage estimators (Lasso) (62J07) Linear regression; mixed models (62J05) Inequalities; stochastic orderings (60E15)

Related Items

Group sparse recovery via group square-root elastic net and the iterative multivariate thresholding-based algorithm, A dual semismooth Newton based augmented Lagrangian method for large-scale linearly constrained sparse group square-root Lasso problems, Correcting for unknown errors in sparse high-dimensional function approximation, A two-stage regularization method for variable selection and forecasting in high-order interaction model, Oracle Inequalities for Local and Global Empirical Risk Minimizers, Improved bounds for square-root Lasso and square-root slope, Unnamed Item, Unnamed Item

Uses Software

• glasso
• flare

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Estimation and testing under sparsity. École d'Été de Probabilités de Saint-Flour XLV -- 2015
• SLOPE is adaptive to unknown sparsity and asymptotically minimax
• Statistics for high-dimensional data. Methods, theory and applications.
• Oracle inequalities in empirical risk minimization and sparse recovery problems. École d'Été de Probabilités de Saint-Flour XXXVIII-2008.
• Nuclear-norm penalization and optimal rates for noisy low-rank matrix completion
• SLOPE-adaptive variable selection via convex optimization
• Adaptive estimation of a quadratic functional by model selection.
• Regularizers for structured sparsity
• Pivotal estimation via square-root lasso in nonparametric regression
• Simultaneous analysis of Lasso and Dantzig selector
• Noisy low-rank matrix completion with general sampling distribution
• Aggregation for Gaussian regression
• Optimization with Sparsity-Inducing Penalties
• Square-root lasso: pivotal recovery of sparse signals via conic programming
• Scaled sparse linear regression
• Aggregation and Sparsity Via ℓ1 Penalized Least Squares
• The Group Square-Root Lasso: Theoretical Properties and Fast Algorithms
• Weakly decomposable regularization penalties and structured sparsity
• The Lasso, correlated design, and improved oracle inequalities
• Convex analysis and monotone operator theory in Hilbert spaces