On the impact of predictor geometry on the performance on high-dimensional ridge-regularized generalized robust regression estimators

DOI10.1007/s00440-016-0754-9zbMath1407.62060OpenAlexW2581138301MaRDI QIDQ681518

Noureddine El Karoui

Publication date: 12 February 2018

Published in: Probability Theory and Related Fields (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1007/s00440-016-0754-9

zbMATH Keywords

random matrix theoryconcentration of measurerobust regressionhigh-dimensional inferenceproximal mappingregression M-estimates

Mathematics Subject Classification ID

Multivariate distribution of statistics (62H10) Asymptotic distribution theory in statistics (62E20) Linear regression; mixed models (62J05) Robustness and adaptive procedures (parametric inference) (62F35) Limit theorems in probability theory (60F99)

Related Items

Fundamental barriers to high-dimensional regression with convex penalties, The asymptotic distribution of the MLE in high-dimensional logistic models: arbitrary covariance, A precise high-dimensional asymptotic theory for boosting and minimum-\(\ell_1\)-norm interpolated classifiers, Nonconvex Low-Rank Tensor Completion from Noisy Data, Conditional predictive inference for stable algorithms, Convex and Nonconvex Optimization Are Both Minimax-Optimal for Noisy Blind Deconvolution Under Random Designs, Gradient descent with random initialization: fast global convergence for nonconvex phase retrieval, Noisy linear inverse problems under convex constraints: exact risk asymptotics in high dimensions, Universality of regularized regression estimators in high dimensions, The existence of maximum likelihood estimate in high-dimensional binary response generalized linear models, Moderate-Dimensional Inferences on Quadratic Functionals in Ordinary Least Squares, Noisy Matrix Completion: Understanding Statistical Guarantees for Convex Relaxation via Nonconvex Optimization, High-dimensional asymptotics of prediction: ridge regression and classification, The likelihood ratio test in high-dimensional logistic regression is asymptotically a rescaled Chi-square, Asymptotic properties on high-dimensional multivariate regression M-estimation, High-dimensional linear models: a random matrix perspective, The distribution of the Lasso: uniform control over sparse balls and adaptive parameter tuning, Spectral method and regularized MLE are both optimal for top-\(K\) ranking, Critical behavior and universality classes for an algorithmic phase transition in sparse reconstruction, Precise statistical analysis of classification accuracies for adversarial training, Exact minimax risk for linear least squares, and the lower tail of sample covariance matrices, An \({\ell_p}\) theory of PCA and spectral clustering, Asymptotic normality of robust \(M\)-estimators with convex penalty, Penalization-induced shrinking without rotation in high dimensional GLM regression: a cavity analysis

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• High dimensional robust M-estimation: asymptotic variance via approximate message passing
• A central limit theorem applicable to robust regression estimators
• High-dimensionality effects in the Markowitz problem and other quadratic programs with linear constraints: risk underestimation
• Concentration of measure and spectra of random matrices: applications to correlation matrices, elliptical distributions and beyond
• Asymptotic behavior of M-estimators of p regression parameters when \(p^ 2/n\) is large. I. Consistency
• Asymptotic behavior of M estimators of p regression parameters when \(p^ 2/n\) is large. II: Normal approximation
• Asymptotic behavior of the empiric distribution of M-estimated residuals from a regression model with many parameters
• On the limit of the largest eigenvalue of the large dimensional sample covariance matrix
• Asymptotics with increasing dimension for robust regression with applications to the bootstrap
• The jackknife estimate of variance
• Robust regression: Asymptotics, conjectures and Monte Carlo
• Rigorous solution of the Gardner problem
• Asymptotics of graphical projection pursuit
• On robust regression with high-dimensional predictors
• Asymptotic Statistics
• Can we trust the bootstrap in high-dimension?
• The LASSO Risk for Gaussian Matrices
• Geometric Representation of High Dimension, Low Sample Size Data
• Proximité et dualité dans un espace hilbertien
• The 1972 Wald Lecture Robust Statistics: A Review
• Probability
• Convergence of stochastic processes