On concentration for (regularized) empirical risk minimization

DOI10.1007/s13171-017-0111-9zbMath1380.62085arXiv1512.00677OpenAlexW2963320582MaRDI QIDQ1688423

Martin J. Wainwright, Sara van de Geer

Publication date: 5 January 2018

Published in: Sankhyā. Series A (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1512.00677

zbMATH Keywords

empirical processdensity estimationconcentrationempirical risk minimizationpenalized least squaresnormal sequence model

Mathematics Subject Classification ID

Asymptotic distribution theory in statistics (62E20) Limit theorems in probability theory (60F99)

Related Items

On least squares estimation under heteroscedastic and heavy-tailed errors, Slope heuristics and V-Fold model selection in heteroscedastic regression using strongly localized bases, Discussion of ``On concentration for (regularized) empirical risk minimization by Sara van de Geer and Martin Wainwright, Concentration behavior of the penalized least squares estimator, Noisy linear inverse problems under convex constraints: exact risk asymptotics in high dimensions, High-dimensional CLT: improvements, non-uniform extensions and large deviations, Nonparametric shape-restricted regression, Sharp oracle inequalities for least squares estimators in shape restricted regression, On tight bounds for the Lasso, Set structured global empirical risk minimizers are rate optimal in general dimensions

Cites Work

• Unnamed Item
• Unnamed Item
• A new perspective on least squares under convex constraint
• Oracle inequalities in empirical risk minimization and sparse recovery problems. École d'Été de Probabilités de Saint-Flour XXXVIII-2008.
• A high-dimensional Wilks phenomenon
• The Brunn-Minkowski inequality in Gauss space
• Left concentration inequalities for empirical processes
• Concentration around the mean for maxima of empirical processes
• Concentration of measure and isoperimetric inequalities in product spaces
• Weak convergence and empirical processes. With applications to statistics
• Optimal upper and lower bounds for the true and empirical excess risks in heteroscedastic least-squares regression
• Penalized least squares estimation in the additive model with different smoothness for the components
• Convex Analysis
• Some applications of concentration inequalities to statistics