Symmetrization approach to concentration inequalities for empirical processes.
From MaRDI portal
Publication:1433892
DOI10.1214/AOP/1068646378zbMATH Open1042.60008arXivmath/0405354OpenAlexW1970535046WikidataQ105584315 ScholiaQ105584315MaRDI QIDQ1433892FDOQ1433892
Authors: D. Panchenko 
Publication date: 1 July 2004
Published in: The Annals of Probability (Search for Journal in Brave)
Abstract: We introduce a symmetrization technique that allows us to translate a problem of controlling the deviation of some functionals on a product space from their mean into a problem of controlling the deviation between two independent copies of the functional. As an application we give a new easy proof of Talagrand's concentration inequality for empirical processes, where besides symmetrization we use only Talagrand's concentration inequality on the discrete cube {-1,+1}^n. As another application of this technique we prove new Vapnik-Chervonenkis type inequalities. For example, for VC-classes of functions we prove a classical inequality of Vapnik and Chervonenkis only with normalization by the sum of variance and sample variance.
Full work available at URL: https://arxiv.org/abs/math/0405354
Recommendations
- New concentration inequalities for suprema of empirical processes
- Left concentration inequalities for empirical processes
- A note on Talagrand's concentration inequality
- Concentration inequalities and asymptotic results for ratio type empirical processes
- A sharp concentration inequality with applications
Cites Work
- Weak convergence and empirical processes. With applications to statistics
- Title not available (Why is that?)
- New concentration inequalities in product spaces
- Title not available (Why is that?)
- A Bennett concentration inequality and its application to suprema of empirical processes
- About the constants in Talagrand's concentration inequalities for empirical processes.
- Uniform Central Limit Theorems
- Une inégalité de Bennett pour les maxima de processus empiriques. (A Bennet type inequality for maxima of empirical processes)
- Concentration inequalities using the entropy method
- When is the Student \(t\)-statistic asymptotically standard normal?
- Concentration of measure and isoperimetric inequalities in product spaces
- Sphere packing numbers for subsets of the Boolean \(n\)-cube with bounded Vapnik-Chervonenkis dimension
- Self-normalized large deviations
- On Talagrand's deviation inequalities for product measures
- A sharp concentration inequality with applications
- Concentration inequalities for set-indexed empirical processes
- Information inequalities and concentration of measure
- Title not available (Why is that?)
- A note on Talagrand's concentration inequality
- Some extensions of an inequality of Vapnik and Chervonenkis
- Left concentration inequalities for empirical processes
Cited In (16)
- Relative deviation learning bounds and generalization with unbounded loss functions
- Sample average approximation with heavier tails. I: Non-asymptotic bounds with weak assumptions and stochastic constraints
- Variance-based extragradient methods with line search for stochastic variational inequalities
- Sample average approximation with heavier tails II: localization in stochastic convex optimization and persistence results for the Lasso
- Exponential bounds for regularized Hotelling's T2 statistic in high dimension
- Density estimation with quadratic loss: a confidence intervals method
- Iterative feature selection in least square regression estimation
- Concentration around the mean for maxima of empirical processes
- A note on Talagrand's concentration inequality
- Measuring distributional asymmetry with Wasserstein distance and Rademacher symmetrization
- Concentration inequalities and asymptotic results for ratio type empirical processes
- Lasso, iterative feature selection and the correlation selector: oracle inequalities and numerical performances
- Complexities of convex combinations and bounding the generalization error in classification
- Sieve Estimation of a Class of Partially Linear Transformation Models With Interval-Censored Competing Risks Data
- A heuristic adaptive fast gradient method in stochastic optimization problems
- Theory of Classification: a Survey of Some Recent Advances
This page was built for publication: Symmetrization approach to concentration inequalities for empirical processes.
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q1433892)
