Moving beyond sub-Gaussianity in high-dimensional statistics: applications in covariance estimation and linear regression

DOI10.1093/imaiai/iaac012OpenAlexW4226270271MaRDI QIDQ5878244

Abhishek Chakrabortty, Arun Kumar Kuchibhotla

Publication date: 20 February 2023

Published in: Information and Inference: A Journal of the IMA (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1804.02605

zbMATH Keywords

empirical processesconcentration inequalitiesrestricted eigenvalue conditionOrlicz normssub-Weibull random variableshigh-dimensional linear regression and Lassostructured covariance matrix estimation

Mathematics Subject Classification ID

Statistics (62-XX)

Related Items (9)

Optimal tail exponents in general last passage percolation via bootstrapping \& geodesic geometry ⋮ High-dimensional central limit theorems for homogeneous sums ⋮ Reinforcement Learning for Linear-Convex Models with Jumps via Stability Analysis of Feedback Controls ⋮ The lower tail of \(q\)-pushTASEP ⋮ Sharp convergence rates for empirical optimal transport with smooth costs ⋮ From \(p\)-Wasserstein bounds to moderate deviations ⋮ Stochastic Saddle Point Problems with Decision-Dependent Distributions ⋮ High-dimensional functional graphical model structure learning via neighborhood selection approach ⋮ Unnamed Item

This page was built for publication: Moving beyond sub-Gaussianity in high-dimensional statistics: applications in covariance estimation and linear regression