A Bennett concentration inequality and its application to suprema of empirical processes
From MaRDI portal
Publication:1600147
DOI10.1016/S1631-073X(02)02292-6zbMath1001.60021MaRDI QIDQ1600147
Publication date: 15 December 2002
Published in: Comptes Rendus. Mathématique. Académie des Sciences, Paris (Search for Journal in Brave)
Related Items
Upper functions for \(\mathbb{L}_{p}\)-norms of Gaussian random fields ⋮ Learning performance of regularized moving least square regression ⋮ The shattering dimension of sets of linear functionals. ⋮ Complexity regularization via localized random penalties ⋮ A reproducing kernel Hilbert space approach to high dimensional partially varying coefficient model ⋮ Local Rademacher complexities and oracle inequalities in risk minimization. (2004 IMS Medallion Lecture). (With discussions and rejoinder) ⋮ Concentration inequalities, counting processes and adaptive statistics ⋮ Statistical properties of kernel principal component analysis ⋮ On the geometry of polytopes generated by heavy-tailed random vectors ⋮ Unnamed Item ⋮ Adaptive sup-norm estimation of the Wigner function in noisy quantum homodyne tomography ⋮ Stability and minimax optimality of tangential Delaunay complexes for manifold reconstruction ⋮ Fast learning rate of non-sparse multiple kernel learning and optimal regularization strategies ⋮ Fast rates for empirical vector quantization ⋮ Upper functions for positive random functionals. I: General setting and Gaussian random functions ⋮ Risk bounds for statistical learning ⋮ Inverse statistical learning ⋮ Local Rademacher complexity: sharper risk bounds with and without unlabeled samples ⋮ The Bernstein-Orlicz norm and deviation inequalities ⋮ Convergence rates for empirical barycenters in metric spaces: curvature, convexity and extendable geodesics ⋮ Sharp large deviation results for sums of independent random variables ⋮ Sparsity in multiple kernel learning ⋮ Learning rates for partially linear functional models with high dimensional scalar covariates ⋮ Sparse quantile regression ⋮ About the rate function in Talagrand's inequality for empirical processes ⋮ Nonasymptotic one- and two-sample tests in high dimension with unknown covariance structure ⋮ Robust matrix estimations meet Frank-Wolfe algorithm ⋮ A Bernstein-type inequality for suprema of random processes with applications to model selection in non-Gaussian regression ⋮ Statistical performance of support vector machines ⋮ High-dimensional generalized linear models and the lasso ⋮ Thermodynamics and concentration ⋮ Model selection: from theory to practice ⋮ Improving Hoeffding's inequality using higher moments information ⋮ High-dimensional local linear regression under sparsity and convex losses ⋮ Interpolation via weighted \(\ell_{1}\) minimization ⋮ Empirical risk minimization is optimal for the convex aggregation problem ⋮ Optimal upper and lower bounds for the true and empirical excess risks in heteroscedastic least-squares regression ⋮ Blockwise SVD with error in the operator and application to blind deconvolution ⋮ A limited in bandwidth uniformity for the functional limit law of the increments of the empirical process ⋮ General oracle inequalities for model selection ⋮ An oracle approach for interaction neighborhood estimation in random fields ⋮ Optimal model selection in density estimation ⋮ On the Bennett-Hoeffding inequality ⋮ Adaptive density estimation of stationary \(\beta\)-mixing and \(\tau\)-mixing processes ⋮ Hoeffding's inequality for supermartingales ⋮ Learning with Convex Loss and Indefinite Kernels ⋮ Optimal model selection for density estimation of stationary data under various mixing condi\-tions ⋮ Uniform in bandwidth exact rates for a class of kernel estimators ⋮ Classification with non-i.i.d. sampling ⋮ Uniform bounds for norms of sums of independent random functions ⋮ U-Processes and Preference Learning ⋮ New concentration inequalities for suprema of empirical processes ⋮ Characterization of LIL behavior in Banach space ⋮ Concentration inequalities using the entropy method ⋮ Symmetrization approach to concentration inequalities for empirical processes. ⋮ Kernel Meets Sieve: Post-Regularization Confidence Bands for Sparse Additive Model ⋮ On higher order isotropy conditions and lower bounds for sparse quadratic forms ⋮ Partitioning a macroscopic system into independent subsystems ⋮ Unnamed Item ⋮ Oracle inequalities for sparse additive quantile regression in reproducing kernel Hilbert space ⋮ Asymptotics for panel quantile regression models with individual effects ⋮ On polynomial time methods for exact low-rank tensor completion ⋮ Convergence rates for the generalized Fréchet mean via the quadruple inequality ⋮ Moment inequalities for functions of independent random variables ⋮ Concentration inequalities and asymptotic results for ratio type empirical processes ⋮ Compensator and exponential inequalities for some suprema of counting processes ⋮ Unnamed Item ⋮ Unnamed Item ⋮ Forward regression for Cox models with high-dimensional covariates ⋮ Concentration around the mean for maxima of empirical processes ⋮ A high-dimensional Wilks phenomenon ⋮ Fast rates for support vector machines using Gaussian kernels ⋮ Variance-based regularization with convex objectives ⋮ Sparse recovery in bounded Riesz systems with applications to numerical methods for PDEs ⋮ Sharp oracle inequalities and slope heuristic for specification probabilities estimation in discrete random fields ⋮ Bandwidth selection in kernel empirical risk minimization via the gradient ⋮ Nearly optimal robust mean estimation via empirical characteristic function ⋮ Adaptive density estimation on bounded domains ⋮ Measuring the Capacity of Sets of Functions in the Analysis of ERM ⋮ Concentration inequalities for bounded functionals via log-Sobolev-type inequalities ⋮ Direct importance estimation for covariate shift adaptation ⋮ Theory of Classification: a Survey of Some Recent Advances ⋮ Moving quantile regression ⋮ On the Optimality of Sample-Based Estimates of the Expectation of the Empirical Minimizer ⋮ Uniform convergence rate of the kernel regression estimator adaptive to intrinsic dimension in presence of censored data ⋮ Modified log-Sobolev inequalities, Beckner inequalities and moment estimates ⋮ Adaptive regression with Brownian path covariate ⋮ Nonparametric estimation of low rank matrix valued function ⋮ High-dimensional additive modeling ⋮ Concentration inequalities for functions of independent variables ⋮ Robust group synchronization via cycle-edge message passing ⋮ Estimation of Censored Quantile Regression for Panel Data With Fixed Effects ⋮ Local Rademacher complexities ⋮ High dimensional generalized linear models for temporal dependent data ⋮ Entropy and Concentration
Cites Work
- About the constants in Talagrand's concentration inequalities for empirical processes.
- On Talagrand's deviation inequalities for product measures
- A sharp concentration inequality with applications
- Concentration inequalities for set-indexed empirical processes
- New concentration inequalities in product spaces
- Unnamed Item
