On the optimality of the empirical risk minimization procedure for the convex aggregation problem

DOI10.1214/11-AIHP458zbMath1259.62038MaRDI QIDQ1943331

Guillaume Lecué, Shahar Mendelson

Publication date: 19 March 2013

Published in: Annales de l'Institut Henri Poincaré. Probabilités et Statistiques (Search for Journal in Brave)

Full work available at URL: https://projecteuclid.org/euclid.aihp/1359470136

zbMATH Keywords

learning theory; aggregation theory; empirical process theory

Mathematics Subject Classification ID

62G08: Nonparametric regression and quantile regression

62G99: Nonparametric inference

Related Items

Optimal Kullback-Leibler aggregation in mixture density estimation by maximum likelihood, On the optimality of the aggregate with exponential weights for low temperatures, Empirical risk minimization is optimal for the convex aggregation problem

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• General nonexact oracle inequalities for classes with a subexponential envelope
• Oracle inequalities in empirical risk minimization and sparse recovery problems. École d'Été de Probabilités de Saint-Flour XXXVIII-2008.
• Empirical processes with a bounded \(\psi_1\) diameter
• Aggregation via empirical risk minimization
• Obtaining fast error rates in nonconvex situations
• Aggregating regression procedures to improve performance
• Lectures on probability theory and statistics. École d'Été de Probabilités de Saint-Flour XXVIII - 1998. Summer school, Saint-Flour, France, August 17 -- September 3, 1998
• Mixing strategies for density estimation.
• Functional aggregation for nonparametric regression.
• \(5n\) Minkowski symmetrizations suffice to arrive at an approximate Euclidean ball
• 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
• \(\ell _{1}\)-regularized linear regression: persistence and oracle inequalities
• Local Rademacher complexities and oracle inequalities in risk minimization. (2004 IMS Medallion Lecture). (With discussions and rejoinder)
• Fast learning rates in statistical inference through aggregation
• Aggregation for Gaussian regression
• Reconstruction and subgaussian operators in asymptotic geometric analysis
• Model selection via testing: an alternative to (penalized) maximum likelihood estimators.
• Empirical minimization
• Sequential Procedures for Aggregating Arbitrary Estimators of a Conditional Mean
• Learning Theory and Kernel Machines
• Aggregation by Exponential Weighting and Sharp Oracle Inequalities