Aggregated estimators and empirical complexity for least square regression
From MaRDI portal
Publication:1888821
DOI10.1016/j.anihpb.2003.11.006zbMath1052.62037OpenAlexW2101718974MaRDI QIDQ1888821
Publication date: 29 November 2004
Published in: Annales de l'Institut Henri Poincaré. Probabilités et Statistiques (Search for Journal in Brave)
Full work available at URL: http://www.numdam.org/item?id=AIHPB_2004__40_6_685_0
Boostingminimax boundsbinary classificationAdaptive estimatorBayesian expected risk boundDeviation inequalitiesOracle inequalities
Nonparametric regression and quantile regression (62G08) Classification and discrimination; cluster analysis (statistical aspects) (62H30) Measures of information, entropy (94A17)
Related Items
PAC-Bayesian high dimensional bipartite ranking, Fast learning rates in statistical inference through aggregation, Variance function estimation in regression model via aggregation procedures, Aggregation of estimators and stochastic optimization, On the optimality of the empirical risk minimization procedure for the convex aggregation problem, Empirical risk minimization is optimal for the convex aggregation problem, Classification via local multi-resolution projections, PAC-Bayesian estimation and prediction in sparse additive models, General oracle inequalities for model selection, PAC-Bayesian bounds for sparse regression estimation with exponential weights, Model selection for weakly dependent time series forecasting, Aggregation for Gaussian regression, Deviation optimal learning using greedy \(Q\)-aggregation, Iterative feature selection in least square regression estimation, A universal procedure for aggregating estimators, PAC-Bayesian bounds for randomized empirical risk minimizers, Aggregation using input-output trade-off, Square root penalty: Adaption to the margin in classification and in edge estimation, Aggregating estimates by convex optimization, Complexities of convex combinations and bounding the generalization error in classification
