Discussion of ``On concentration for (regularized) empirical risk minimization by Sara van de Geer and Martin Wainwright

DOI10.1007/s13171-017-0113-7zbMath1380.62076OpenAlexW2753130570MaRDI QIDQ1688424

Stéphane Boucheron

Publication date: 5 January 2018

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

Full work available at URL: https://doi.org/10.1007/s13171-017-0113-7

zbMATH Keywords

penalizationconcentration inequalitiesWilks phenomenonrisk estimates

Mathematics Subject Classification ID

Asymptotic distribution theory in statistics (62E20)

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• A new perspective on least squares under convex constraint
• Statistics for high-dimensional data. Methods, theory and applications.
• Poincaré's inequalities and Talagrand's concentration phenomenon for the exponential distribution
• A high-dimensional Wilks phenomenon
• Risk bounds for statistical learning
• On concentration for (regularized) empirical risk minimization
• Optimal model selection in heteroscedastic regression using piecewise polynomial functions
• Local Rademacher complexities and oracle inequalities in risk minimization. (2004 IMS Medallion Lecture). (With discussions and rejoinder)
• Towards the study of least squares estimators with convex penalty