A new perspective on least squares under convex constraint

DOI10.1214/14-AOS1254zbMath1302.62053arXiv1402.0830MaRDI QIDQ482891

Sourav Chatterjee

Publication date: 6 January 2015

Published in: The Annals of Statistics (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1402.0830

zbMATH Keywords

maximum likelihoodleast squaresempirical processdenoisingisotonic regressionlassoconvex constraint

Mathematics Subject Classification ID

Asymptotic properties of parametric estimators (62F12) Nonparametric regression and quantile regression (62G08) Point estimation (62F10) Parametric inference under constraints (62F30)

Related Items

High-dimensional asymptotics of likelihood ratio tests in the Gaussian sequence model under convex constraints ⋮ An improved global risk bound in concave regression ⋮ Adaptation in multivariate log-concave density estimation ⋮ The phase transition for the existence of the maximum likelihood estimate in high-dimensional logistic regression ⋮ Slope heuristics and V-Fold model selection in heteroscedastic regression using strongly localized bases ⋮ Estimating piecewise monotone signals ⋮ The limiting behavior of isotonic and convex regression estimators when the model is misspecified ⋮ On concentration for (regularized) empirical risk minimization ⋮ Discussion of ``On concentration for (regularized) empirical risk minimization by Sara van de Geer and Martin Wainwright ⋮ Discussion of the paper ``On concentration for (regularized) empirical risk minimization ⋮ Concentration behavior of the penalized least squares estimator ⋮ Noisy linear inverse problems under convex constraints: exact risk asymptotics in high dimensions ⋮ From Gauss to Kolmogorov: localized measures of complexity for ellipses ⋮ High-dimensional estimation with geometric constraints: Table 1. ⋮ Estimation of Monge matrices ⋮ Adaptive risk bounds in unimodal regression ⋮ Optimal rates of statistical seriation ⋮ Nonparametric shape-restricted regression ⋮ Bayesian fractional posteriors ⋮ The geometry of hypothesis testing over convex cones: generalized likelihood ratio tests and minimax radii ⋮ Isotonic regression meets Lasso ⋮ Oracle inequalities for high-dimensional prediction ⋮ Sharp oracle inequalities for least squares estimators in shape restricted regression ⋮ On the sensitivity of the Lasso to the number of predictor variables ⋮ Estimation in High Dimensions: A Geometric Perspective ⋮ Estimating a density, a hazard rate, and a transition intensity via the \(\rho\)-estimation method ⋮ Inverse Optimization with Noisy Data ⋮ Set structured global empirical risk minimizers are rate optimal in general dimensions ⋮ Hypothesis testing for densities and high-dimensional multinomials: sharp local minimax rates ⋮ Localized Gaussian width of \(M\)-convex hulls with applications to Lasso and convex aggregation ⋮ Isotonic regression in general dimensions ⋮ Stratified incomplete local simplex tests for curvature of nonparametric multiple regression ⋮ Suboptimality of constrained least squares and improvements via non-linear predictors

Uses Software

• ElemStatLearn

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• The Adaptive Lasso and Its Oracle Properties
• Sharp MSE bounds for proximal denoising
• Degrees of freedom in lasso problems
• Adaptivity and optimality of the monotone least-squares estimator
• Statistics for high-dimensional data. Methods, theory and applications.
• Exponential screening and optimal rates of sparse estimation
• A new approach to least-squares estimation, with applications
• The Dantzig selector and sparsity oracle inequalities
• From Steiner formulas for cones to concentration of intrinsic volumes
• Concentration inequalities and model selection. Ecole d'Eté de Probabilités de Saint-Flour XXXIII -- 2003.
• Estimating a regression function
• Lasso-type recovery of sparse representations for high-dimensional data
• Asymptotic normality of statistics based on the convex minorants of empirical distribution functions
• The Brunn-Minkowski inequality in Gauss space
• Extremal properties of half-spaces for spherically invariant measures
• Rates of convergence for minimum contrast estimators
• Consistency for the least squares estimator in nonparametric regression
• Sharp asymptotics for isotonic regression
• Persistene in high-dimensional linear predictor-selection and the virtue of overparametrization
• On the degrees of freedom in shape-restricted regression.
• Asymptotics for Lasso-type estimators.
• Risk bounds in isotonic regression
• Least angle regression. (With discussion)
• Weak convergence and empirical processes. With applications to statistics
• The convex geometry of linear inverse problems
• \(\ell _{1}\)-regularized linear regression: persistence and oracle inequalities
• Convergence of linear functionals of the Grenander estimator under misspecification
• Hellinger-consistency of certain nonparametric maximum likelihood estimators
• Simultaneous analysis of Lasso and Dantzig selector
• High-dimensional generalized linear models and the lasso
• Sparsity oracle inequalities for the Lasso
• On the ``degrees of freedom of the lasso
• The Dantzig selector: statistical estimation when \(p\) is much larger than \(n\). (With discussions and rejoinder).
• High-dimensional graphs and variable selection with the Lasso
• On risk bounds in isotonic and other shape restricted regression problems
• The sizes of compact subsets of Hilbert space and continuity of Gaussian processes
• An Empirical Distribution Function for Sampling with Incomplete Information
• On sparse reconstruction from Fourier and Gaussian measurements
• Decoding by Linear Programming
• Stable recovery of sparse overcomplete representations in the presence of noise
• Unified LASSO Estimation by Least Squares Approximation
• Ideal spatial adaptation by wavelet shrinkage
• Uncertainty principles and ideal atomic decomposition
• Asymptotic behavior of the grenander estimator at density flat regions
• Sharp Thresholds for High-Dimensional and Noisy Sparsity Recovery Using $\ell _{1}$-Constrained Quadratic Programming (Lasso)
• Computational and statistical tradeoffs via convex relaxation
• Living on the edge: phase transitions in convex programs with random data
• The L₂risk of an isotonic estimate
• Corrupted Sensing: Novel Guarantees for Separating Structured Signals
• Optimally sparse representation in general (nonorthogonal) dictionaries via ℓ ¹ minimization
• For most large underdetermined systems of equations, the minimal 𝓁₁‐norm near‐solution approximates the sparsest near‐solution
• The Lasso, correlated design, and improved oracle inequalities
• Probability
• Convergence of stochastic processes