Aggregation and minimax optimality in high-dimensional estimation

zbMATH Open1380.62136MaRDI QIDQ4589004FDOQ4589004

Authors: Alexandre B. Tsybakov 

Publication date: 6 November 2017

Recommendations

• Learning Theory and Kernel Machines
• Generalized mirror averaging and \(D\)-convex aggregation
• Aggregation via empirical risk minimization
• Aggregation by Exponential Weighting and Sharp Oracle Inequalities
• A universal procedure for aggregating estimators

zbMATH Keywords

aggregationsparsityoracle inequalityminimax estimationexponential weightshigh-dimensional model

Mathematics Subject Classification ID

Nonparametric estimation (62G05) Ridge regression; shrinkage estimators (Lasso) (62J07)

Cited In (16)

• Targeting underrepresented populations in precision medicine: a federated transfer learning approach
• Localized Gaussian width of \(M\)-convex hulls with applications to Lasso and convex aggregation
• Exponential screening and optimal rates of sparse estimation
• Optimal Kullback-Leibler aggregation in mixture density estimation by maximum likelihood
• Structured, sparse aggregation
• Optimal bounds for aggregation of affine estimators
• Oracle posterior contraction rates under hierarchical priors
• A general framework for Bayes structured linear models
• Estimation of matrices with row sparsity
• Variance function estimation in regression model via aggregation procedures
• Simple proof of the risk bound for denoising by exponential weights for asymmetric noise distributions
• On the asymptotic aggregation of high dimensional systems
• On the exponentially weighted aggregate with the Laplace prior
• Transfer Learning in Large-Scale Gaussian Graphical Models with False Discovery Rate Control
• Aggregating estimates by convex optimization
• Rate optimal estimation of quadratic functionals in inverse problems with partially unknown operator and application to testing problems

This page was built for publication: Aggregation and minimax optimality in high-dimensional estimation

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4589004)