Upper bounds on product and multiplier empirical processes

DOI10.1016/J.SPA.2016.04.019MaRDI QIDQ335637zbMATH OpenOpenAlexFDO

Authors Shahar Mendelson

Publication date 2 November 2016

Published in Stochastic Processes and their Applications (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/1410.8003

zbMATH Keywords

empirical processesgeneric chaining

Mathematics Subject Classification ID

Gaussian processes (60G15) Inequalities; stochastic orderings (60E15) Central limit and other weak theorems (60F05) Functional limit theorems; invariance principles (60F17)

Abstract: We study two empirical process of special structure: firstly, the centred multiplier process indexed by a class $F$, $foleft|su{m}_{i=1}^N(x{i}_{i}f(X_i)-Exif)ight|$, where the i.i.d. multipliers $(x{i}_i{)}_{i=1}^N$ need not be independent of $(X_i{)}_{i=1}^N$, and secondly, $(f,h)oleft|su{m}_{i=1}^N(f(X_i)h(X_i)-Efh)ight|$, the centred product process indexed by the classes $F$ and $H$. We use chaining methods to obtain high probability upper bounds on the suprema of the two processes using a natural variation of Talagrand's $gamma$-functionals.

Recommendations

• Bounds for stochastic processes on product index spaces
• scientific article; zbMATH DE number 51427
• Sharper bounds for Gaussian and empirical processes
• Upper functions for positive random functionals. II. Application to the empirical processes theory. I
• On weakly bounded empirical processes

Cites work

• scientific article; zbMATH DE number 3518027 (Why is no real title available?)
• scientific article; zbMATH DE number 1975220 (Why is no real title available?)
• A note on suprema of canonical processes based on random variables with regular moments
• Empirical processes with a bounded \(\psi_1\) diameter
• Estimation of moments of sums of independent real random variables
• Learning without concentration
• Learning without concentration for general loss functions
• On generic chaining and the smallest singular value of random matrices with heavy tails
• Reconstruction and subgaussian operators in asymptotic geometric analysis
• Regularity of Gaussian processes
• Some limit theorems for empirical processes (with discussion)
• Tail and moment estimates for sums of independent random variables with logarithmically concave tails
• Tail bounds via generic chaining
• The Distribution of Rademacher Sums
• The Supremum of Some Canonical Processes
• Uniform Central Limit Theorems
• Upper and lower bounds for stochastic processes. Modern methods and classical problems
• Weak convergence and empirical processes. With applications to statistics

Cited in

(19)

• Non-convex projected gradient descent for generalized low-rank tensor regression
• On least squares estimation under heteroscedastic and heavy-tailed errors
• Regularization and the small-ball method. I: Sparse recovery
• Robust covariance estimation under \(L_4\)-\(L_2\) norm equivalence
• Random embeddings with an almost Gaussian distortion
• Bounds for stochastic processes on product index spaces
• Slope meets Lasso: improved oracle bounds and optimality
• Convergence rates of least squares regression estimators with heavy-tailed errors
• Regularization and the small-ball method. II: Complexity dependent error rates
• Optimal estimation and computational limit of low-rank Gaussian mixtures
• Large deviation properties for empirical quantile-type production functions
• A unified approach to uniform signal recovery from nonlinear observations
• Extending the scope of the small-ball method
• On multiplier processes under weak moment assumptions
• Uniform recovery guarantees for quantized corrupted sensing using structured or generative priors
• On aggregation for heavy-tailed classes
• Generic error bounds for the generalized Lasso with sub-exponential data
• Multiplier \(U\)-processes: sharp bounds and applications
• Learning without concentration for general loss functions

This page was built for publication: Upper bounds on product and multiplier empirical processes

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q335637)