Aggregation via empirical risk minimization

DOI10.1007/s00440-008-0180-8zbMath1206.62094OpenAlexW2103619557MaRDI QIDQ842390

Guillaume Lecué, Shahar Mendelson

Publication date: 25 September 2009

Published in: Probability Theory and Related Fields (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1007/s00440-008-0180-8

Mathematics Subject Classification ID

Order statistics; empirical distribution functions (62G30) Statistical decision theory (62C99) Nonparametric inference (62G99)

Related Items

On aggregation for heavy-tailed classes, Performance of empirical risk minimization in linear aggregation, Variance function estimation in regression model via aggregation procedures, Unnamed Item, On the optimality of the empirical risk minimization procedure for the convex aggregation problem, Empirical risk minimization is optimal for the convex aggregation problem, Oracle inequalities for cross-validation type procedures, Optimal model selection in heteroscedastic regression using piecewise polynomial functions, On the optimality of the aggregate with exponential weights for low temperatures, Kullback-Leibler aggregation and misspecified generalized linear models, General nonexact oracle inequalities for classes with a subexponential envelope, Aggregation of affine estimators, Optimal learning with \textit{Q}-aggregation, On the uniform convergence of empirical norms and inner products, with application to causal inference, Deviation optimal learning using greedy \(Q\)-aggregation, Optimal learning with Bernstein Online Aggregation, On Martingale Extensions of Vapnik–Chervonenkis Theory with Applications to Online Learning, Non-parametric Poisson regression from independent and weakly dependent observations by model selection, Localized Gaussian width of \(M\)-convex hulls with applications to Lasso and convex aggregation, Distribution-free robust linear regression

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Some limit theorems for empirical processes (with discussion)
• Subspaces and orthogonal decompositions generated by bounded orthogonal systems
• Learning by mirror averaging
• Aggregation by exponential weighting, sharp PAC-Bayesian bounds and sparsity
• Complexity regularization via localized random penalties
• Weak convergence and empirical processes. With applications to statistics
• Optimal rates and adaptation in the single-index model using aggregation
• Aggregation for Gaussian regression
• On weakly bounded empirical processes
• Reconstruction and subgaussian operators in asymptotic geometric analysis
• Sequential Procedures for Aggregating Arbitrary Estimators of a Conditional Mean
• Lower Bounds for the Empirical Minimization Algorithm
• Uniform Central Limit Theorems
• The importance of convexity in learning with squared loss
• Learning Theory and Kernel Machines
• Suboptimality of Penalized Empirical Risk Minimization in Classification
• Convexity, Classification, and Risk Bounds
• Introduction to nonparametric estimation