Pages that link to "Item:Q2373576"

The following pages link to Local Rademacher complexities and oracle inequalities in risk minimization. (2004 IMS Medallion Lecture). (With discussions and rejoinder) (Q2373576):

Displaying 50 items.

• Direct importance estimation for covariate shift adaptation (Q144623) (← links)
• Tikhonov, Ivanov and Morozov regularization for support vector machine learning (Q285946) (← links)
• Fast rates for empirical vector quantization (Q351685) (← links)
• Inverse statistical learning (Q364201) (← links)
• The two-sample problem for Poisson processes: adaptive tests with a nonasymptotic wild bootstrap approach (Q366986) (← links)
• A statistical view of clustering performance through the theory of \(U\)-processes (Q392047) (← links)
• Random design analysis of ridge regression (Q404306) (← links)
• Risk bounds for CART classifiers under a margin condition (Q437488) (← links)
• Concentration inequalities and confidence bands for needlet density estimators on compact homogeneous manifolds (Q438975) (← links)
• General nonexact oracle inequalities for classes with a subexponential envelope (Q447832) (← links)
• Margin-adaptive model selection in statistical learning (Q453298) (← links)
• Optimal exponential bounds on the accuracy of classification (Q485316) (← links)
• A new method for estimation and model selection: \(\rho\)-estimation (Q510164) (← links)
• Adaptive estimation of a distribution function and its density in sup-norm loss by wavelet and spline projections (Q627291) (← links)
• Sharper lower bounds on the performance of the empirical risk minimization algorithm (Q637070) (← links)
• Parametric or nonparametric? A parametricness index for model selection (Q651025) (← links)
• A high-dimensional Wilks phenomenon (Q718891) (← links)
• Approximation properties of certain operator-induced norms on Hilbert spaces (Q765689) (← links)
• Sparsity in penalized empirical risk minimization (Q838303) (← links)
• Regularization in kernel learning (Q847647) (← links)
• Empirical risk minimization for heavy-tailed losses (Q892246) (← links)
• Obtaining fast error rates in nonconvex situations (Q933417) (← links)
• Fast learning rates for plug-in classifiers (Q995418) (← links)
• A universal procedure for aggregating estimators (Q1002171) (← links)
• Sparse recovery in convex hulls via entropy penalization (Q1018643) (← links)
• Measuring distributional asymmetry with Wasserstein distance and Rademacher symmetrization (Q1657945) (← links)
• Fast learning rate of non-sparse multiple kernel learning and optimal regularization strategies (Q1657947) (← links)
• Joint regression analysis of mixed-type outcome data via efficient scores (Q1662937) (← links)
• Localization of VC classes: beyond local Rademacher complexities (Q1663641) (← links)
• Local Rademacher complexity: sharper risk bounds with and without unlabeled samples (Q1669081) (← links)
• Discussion of ``On concentration for (regularized) empirical risk minimization'' by Sara van de Geer and Martin Wainwright (Q1688424) (← links)
• Relative deviation learning bounds and generalization with unbounded loss functions (Q1714946) (← links)
• Bayesian fractional posteriors (Q1731743) (← links)
• Robust multicategory support vector machines using difference convex algorithm (Q1749454) (← links)
• Mass volume curves and anomaly ranking (Q1786577) (← links)
• On the optimality of the empirical risk minimization procedure for the convex aggregation problem (Q1943331) (← links)
• Optimal upper and lower bounds for the true and empirical excess risks in heteroscedastic least-squares regression (Q1950830) (← links)
• Oracle inequalities for cross-validation type procedures (Q1950881) (← links)
• Optimal model selection in heteroscedastic regression using piecewise polynomial functions (Q1951154) (← links)
• General oracle inequalities for model selection (Q1951973) (← links)
• Model selection by resampling penalization (Q1951992) (← links)
• On the optimality of the aggregate with exponential weights for low temperatures (Q1952438) (← links)
• Adaptive kernel methods using the balancing principle (Q1959089) (← links)
• Rho-estimators revisited: general theory and applications (Q1990601) (← links)
• Singularity, misspecification and the convergence rate of EM (Q1996764) (← links)
• Surrogate losses in passive and active learning (Q2008623) (← links)
• Tests and estimation strategies associated to some loss functions (Q2041653) (← links)
• Set structured global empirical risk minimizers are rate optimal in general dimensions (Q2054522) (← links)
• Fast generalization error bound of deep learning without scale invariance of activation functions (Q2055056) (← links)
• Multiplier \(U\)-processes: sharp bounds and applications (Q2073203) (← links)