On multiplier processes under weak moment assumptions

DOI10.1007/978-3-319-45282-1_19zbMATH Open1366.60044arXiv1601.06523OpenAlexW2271052253MaRDI QIDQ5278302FDOQ5278302

Authors: Shahar Mendelson 

Publication date: 13 July 2017

Published in: Lecture Notes in Mathematics (Search for Journal in Brave)

Abstract: We show that if $Vsubset{R}^n$ satisfies a certain symmetry condition (closely related to unconditionaity) and if $X$ is an isotropic random vector for which $|inrX,t{|}_{L_p}leqLsqrtp$ for every $tin{S}^{n-1}$ and $plesssimlogn$, then the corresponding empirical and multiplier processes indexed by $V$ behave as if $X$ were $L$-subgaussian.

Full work available at URL: https://arxiv.org/abs/1601.06523

Recommendations

• On weakly bounded empirical processes
• Upper bounds on product and multiplier empirical processes
• New concentration inequalities for suprema of empirical processes
• Empirical processes with a bounded \(\psi_1\) diameter
• Empirical processes and random projections

Mathematics Subject Classification ID

Probability distributions: general theory (60E05) Stochastic processes (60G99)

Cites Work

• Weak convergence and empirical processes. With applications to statistics
• Statistics for high-dimensional data. Methods, theory and applications.
• Title not available (Why is that?)
• Oracle inequalities in empirical risk minimization and sparse recovery problems. École d'Été de Probabilités de Saint-Flour XXXVIII-2008.
• A mathematical introduction to compressive sensing
• Title not available (Why is that?)
• Asymptotic geometric analysis. I
• Title not available (Why is that?)
• Sparse recovery under weak moment assumptions
• Minimax rate of convergence and the performance of empirical risk minimization in phase recovery
• A remark on the diameter of random sections of convex bodies
• Regularity of Gaussian processes
• Learning without concentration for general loss functions
• Reconstruction and subgaussian operators in asymptotic geometric analysis
• Upper bounds on product and multiplier empirical processes
• On generic chaining and the smallest singular value of random matrices with heavy tails
• Subspaces of Small Codimension of Finite-Dimensional Banach Spaces

Cited In (8)

• Title not available (Why is that?)
• Convergence rates of least squares regression estimators with heavy-tailed errors
• The weak sequential core for two-period economies
• Finite impulse response models: a non-asymptotic analysis of the least squares estimator
• Optimal robust mean and location estimation via convex programs with respect to any pseudo-norms
• Robust statistical learning with Lipschitz and convex loss functions
• Regularization, sparse recovery, and median-of-means tournaments
• Multiplier \(U\)-processes: sharp bounds and applications

This page was built for publication: On multiplier processes under weak moment assumptions

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5278302)