Set structured global empirical risk minimizers are rate optimal in general dimensions
From MaRDI portal
Publication:2054522
DOI10.1214/21-AOS2049zbMath1478.62081arXiv1905.12823OpenAlexW3212589533MaRDI QIDQ2054522
Publication date: 3 December 2021
Published in: The Annals of Statistics (Search for Journal in Brave)
Full work available at URL: https://arxiv.org/abs/1905.12823
classificationempirical processdensity estimationnonparametric regressionempirical risk minimizationnon-Donsker
Nonparametric regression and quantile regression (62G08) Density estimation (62G07) Asymptotic properties of nonparametric inference (62G20) Nonparametric estimation (62G05)
Related Items (7)
Isotonic regression with unknown permutations: statistics, computation and adaptation ⋮ Phase transitions for support recovery under local differential privacy ⋮ Minimax rates for conditional density estimation via empirical entropy ⋮ Coverage of credible intervals in Bayesian multivariate isotonic regression ⋮ Inference for Local Parameters in Convexity Constrained Models ⋮ Posterior contraction and testing for multivariate isotonic regression ⋮ Multiplier \(U\)-processes: sharp bounds and applications
Cites Work
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Global rates of convergence of the MLEs of log-concave and \(s\)-concave densities
- Approximation and estimation of \(s\)-concave densities via Rényi divergences
- Bounding the expectation of the supremum of an empirical process over a (weak) VC-major class
- Optimal rates of convergence for convex set estimation from support functions
- A new perspective on least squares under convex constraint
- Global rates of convergence in log-concave density estimation
- A new approach to least-squares estimation, with applications
- Nonparametric estimation of multivariate convex-transformed densities
- New Donsker classes
- Minimax theory of image reconstruction
- Risk bounds for statistical learning
- Estimating a regression function
- A central limit theorem under metric entropy with \(L_ 2\) bracketing
- Risk bounds for model selection via penalization
- Rates of convergence for minimum contrast estimators
- Information-theoretic determination of minimax rates of convergence
- Smooth discrimination analysis
- On concentration for (regularized) empirical risk minimization
- Efficient maximum likelihood estimation in semiparametric mixture models
- Maximal inequalities via bracketing with adaptive truncation
- Optimal aggregation of classifiers in statistical learning.
- Probability inequalities for likelihood ratios and convergence rates of sieve MLEs
- Asymptotical minimax recovery of sets with smooth boundaries
- The method of sieves and minimum contrast estimators
- Weak convergence and empirical processes. With applications to statistics
- Optimal upper and lower bounds for the true and empirical excess risks in heteroscedastic least-squares regression
- Adaptive estimation of convex polytopes and convex sets from noisy data
- Convergence rates of least squares regression estimators with heavy-tailed errors
- Isotonic regression in general dimensions
- Hellinger-consistency of certain nonparametric maximum likelihood estimators
- Local Rademacher complexities and oracle inequalities in risk minimization. (2004 IMS Medallion Lecture). (With discussions and rejoinder)
- On matrix estimation under monotonicity constraints
- Simultaneous adaptation to the margin and to complexity in classification
- Entropy estimate for high-dimensional monotonic functions
- Concentration inequalities and asymptotic results for ratio type empirical processes
- Convergence of estimates under dimensionality restrictions
- Mathematical Foundations of Infinite-Dimensional Statistical Models
- Empirical and Poisson processes on classes of sets or functions too large for central limit theorems
- Minimax Two-Dimensional Image Reconstruction
- [https://portal.mardi4nfdi.de/wiki/Publication:4743580 Approximation dans les espaces m�triques et th�orie de l'estimation]
This page was built for publication: Set structured global empirical risk minimizers are rate optimal in general dimensions
