General nonexact oracle inequalities for classes with a subexponential envelope

DOI10.1214/11-AOS965zbMath1274.62247arXiv1206.0871WikidataQ105584286 ScholiaQ105584286MaRDI QIDQ447832

Guillaume Lecué, Shahar Mendelson

Publication date: 29 August 2012

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

Full work available at URL: https://arxiv.org/abs/1206.0871

zbMATH Keywords

classification; aggregation; regularization; model selection; high-dimensional data; oracle inequalities; statistical learning; fast rates of convergence

Mathematics Subject Classification ID

62H30: Classification and discrimination; cluster analysis (statistical aspects)

62G05: Nonparametric estimation

68T10: Pattern recognition, speech recognition

Related Items

Sample average approximation with heavier tails II: localization in stochastic convex optimization and persistence results for the Lasso, Inverse statistical learning, General nonexact oracle inequalities for classes with a subexponential envelope, \(\ell _{1}\)-regularized linear regression: persistence and oracle inequalities, On the optimality of the empirical risk minimization procedure for the convex aggregation problem, Empirical variance minimization with applications in variance reduction and optimal control, Estimation bounds and sharp oracle inequalities of regularized procedures with Lipschitz loss functions, Aggregation of affine estimators, Posterior concentration and fast convergence rates for generalized Bayesian learning

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• The Adaptive Lasso and Its Oracle Properties
• On generic chaining and the smallest singular value of random matrices with heavy tails
• General nonexact oracle inequalities for classes with a subexponential envelope
• Empirical processes with a bounded \(\psi_1\) diameter
• The Dantzig selector and sparsity oracle inequalities
• Sharper lower bounds on the performance of the empirical risk minimization algorithm
• Some sharp performance bounds for least squares regression with \(L_1\) regularization
• Sparsity in penalized empirical risk minimization
• Aggregation via empirical risk minimization
• Regularization in kernel learning
• Risk bounds for statistical learning
• Concentration inequalities and model selection. Ecole d'Eté de Probabilités de Saint-Flour XXXIII -- 2003.
• Obtaining fast error rates in nonconvex situations
• Lasso-type recovery of sparse representations for high-dimensional data
• Sparse recovery in convex hulls via entropy penalization
• A tail inequality for suprema of unbounded empirical processes with applications to Markov chains
• Inequalities of Bernstein-Jackson-type and the degree of compactness of operators in Banach spaces
• Estimation of dependences based on empirical data. Transl. from the Russian by Samuel Kotz
• Risk bounds for model selection via penalization
• Sharper bounds for Gaussian and empirical processes
• Weak convergence and empirical processes. With applications to statistics
• \(\ell _{1}\)-regularized linear regression: persistence and oracle inequalities
• On the optimality of the aggregate with exponential weights for low temperatures
• Local Rademacher complexities and oracle inequalities in risk minimization. (2004 IMS Medallion Lecture). (With discussions and rejoinder)
• Simultaneous analysis of Lasso and Dantzig selector
• High-dimensional generalized linear models and the lasso
• Sparsity oracle inequalities for the Lasso
• Sup-norm convergence rate and sign concentration property of Lasso and Dantzig estimators
• The Dantzig selector: statistical estimation when \(p\) is much larger than \(n\). (With discussions and rejoinder).
• Reconstruction and subgaussian operators in asymptotic geometric analysis
• Empirical minimization
• High-dimensional graphs and variable selection with the Lasso
• Support Vector Machines
• Lower Bounds for the Empirical Minimization Algorithm
• The Generic Chaining
• The importance of convexity in learning with squared loss
• Sparse Approximate Solutions to Linear Systems
• Compressed sensing