``Local vs. ``global parameters -- breaking the Gaussian complexity barrier

DOI10.1214/16-AOS1510zbMath1459.62054arXiv1504.02191OpenAlexW2962892873WikidataQ105584289 ScholiaQ105584289MaRDI QIDQ1687107

Shahar Mendelson

Publication date: 22 December 2017

Published in: The Annals of Statistics (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1504.02191

zbMATH Keywords

covering numberserror ratesGaussian averages

Mathematics Subject Classification ID

Nonparametric regression and quantile regression (62G08) Gaussian processes (60G15) Minimax procedures in statistical decision theory (62C20)

Related Items (9)

On least squares estimation under heteroscedastic and heavy-tailed errors ⋮ Optimal robust mean and location estimation via convex programs with respect to any pseudo-norms ⋮ Localization of VC classes: beyond local Rademacher complexities ⋮ Sample average approximation with heavier tails. I: Non-asymptotic bounds with weak assumptions and stochastic constraints ⋮ Regularization, sparse recovery, and median-of-means tournaments ⋮ Robust one-bit compressed sensing with partial circulant matrices ⋮ When are epsilon-nets small? ⋮ Convergence rates of least squares regression estimators with heavy-tailed errors ⋮ Near-optimal mean estimators with respect to general norms

This page was built for publication: ``Local vs. ``global parameters -- breaking the Gaussian complexity barrier