Nemirovski's inequalities revisited

DOI10.4169/000298910X476059MaRDI QIDQ3060151zbMATH OpenOpenAlexDBLPWikidataFDO

Authors Lutz Dümbgen, Sara Van De Geer, Jon A. Wellner, Mark Veraar

Publication date 1 December 2010

Published in The American Mathematical Monthly (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/0807.2245

zbMATH Keywords

finite second momentsindependent random variablesinequalities for normsvectors in Banach spacevectors in Hilbert space

Mathematics Subject Classification ID

Inequalities; stochastic orderings (60E15)

Abstract: An important tool for statistical research are moment inequalities for sums of independent random vectors. Nemirovski and coworkers (1983, 2000) derived one particular type of such inequalities: For certain Banach spaces $(B,|cdot|)$ there exists a constant $K=K(B,|cdot|)$ such that for arbitrary independent and centered random vectors $X_1,X_2,\mathrm{...},X_{n}inB$, their sum $S_n$ satisfies the inequality $E|S_n{|}^{2}leKsu{m}_{i=1}^{n}E|X_i{|}^2$. We present and compare three different approaches to obtain such inequalities: Nemirovski's results are based on deterministic inequalities for norms. Another possible vehicle are type and cotype inequalities, a tool from probability theory on Banach spaces. Finally, we use a truncation argument plus Bernstein's inequality to obtain another version of the moment inequality above. Interestingly, all three approaches have their own merits.

Recommendations

• Around Nemirovski’s inequality
• scientific article; zbMATH DE number 3971854
• Optimum bounds on moments of sums of independent random vectors
• Comparison of moments of sums of independent random variables and differential inequalities
• Moment inequalities for functions of independent random variables

Cited in

(22)

• D-learning to estimate optimal individual treatment rules
• Measuring distributional asymmetry with Wasserstein distance and Rademacher symmetrization
• Concentration inequalities for separately convex functions
• A conversation with Jon Wellner
• The smooth-Lasso and other \(\ell _{1}+\ell _{2}\)-penalized methods
• On least squares estimation under heteroscedastic and heavy-tailed errors
• Maximal inequalities for stochastic convolutions and pathwise uniform convergence of time discretisation schemes
• Pivotal estimation via square-root lasso in nonparametric regression
• Solving equations of random convex functions via anchored regression
• Randomized first order algorithms with applications to \(\ell _{1}\)-minimization
• Hypercontraction methods in moment inequalities for series of independent random variables in normed spaces
• Local linear smoothing for sparse high dimensional varying coefficient models
• R-boundedness versus -boundedness
• Rosenthal-Type Inequalities for Martingales in 2-Smooth Banach Spaces
• New concentration inequalities for suprema of empirical processes
• Vast portfolio selection with gross-exposure constraints
• On the limits of clustering in high dimensions via cost functions
• On the adaptivity of stochastic gradient-based optimization
• Adaptive sequential sample average approximation for solving two-stage stochastic linear programs
• Oracle inequalities and optimal inference under group sparsity
• Revisiting differentially private stochastic convex optimization in (non)-Euclidean space
• On asymptotically optimal confidence regions and tests for high-dimensional models

This page was built for publication: Nemirovski's inequalities revisited

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q3060151)