General oracle inequalities for model selection

DOI10.1214/08-EJS254zbMath1326.62076arXiv0806.4140MaRDI QIDQ1951973

Charles Mitchell, Sara van de Geer

Publication date: 27 May 2013

Published in: Electronic Journal of Statistics (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/0806.4140

Mathematics Subject Classification ID

Asymptotic properties of nonparametric inference (62G20) Nonparametric estimation (62G05)

Related Items

Kullback-Leibler aggregation and misspecified generalized linear models

Cites Work

• Sharper lower bounds on the performance of the empirical risk minimization algorithm
• Obtaining fast error rates in nonconvex situations
• Learning by mirror averaging
• Risk bounds for model selection via penalization
• A Bennett concentration inequality and its application to suprema of empirical processes
• A distribution-free theory of nonparametric regression
• Optimal aggregation of classifiers in statistical learning.
• Aggregated estimators and empirical complexity for least square regression
• Weak convergence and empirical processes. With applications to statistics
• Local Rademacher complexities and oracle inequalities in risk minimization. (2004 IMS Medallion Lecture). (With discussions and rejoinder)
• Recursive aggregation of estimators by the mirror descent algorithm with averaging
• Aggregation for Gaussian regression
• Optimal rates of aggregation in classification under low noise assumption
• Empirical minimization
• Oracle inequalities for multi-fold cross validation
• Quantization for Nonparametric Regression
• The importance of convexity in learning with squared loss
• A Randomized Online Learning Algorithm for Better Variance Control
• Suboptimality of Penalized Empirical Risk Minimization in Classification
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item