On the uniform convergence of empirical norms and inner products, with application to causal inference

DOI10.1214/14-EJS894zbMATH Open1348.62152WikidataQ130494040 ScholiaQ130494040MaRDI QIDQ2452107FDOQ2452107

Authors Sara Van De Geer 

Publication date 30 May 2014

Published in Electronic Journal of Statistics (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/1310.5523

zbMATH Keywords

causal inferenceuniform convergenceadditive modelempirical measure

Mathematics Subject Classification ID

Nonparametric regression and quantile regression (62G08) Asymptotic properties of nonparametric inference (62G20)

Abstract: Uniform convergence of empirical norms - empirical measures of squared functions - is a topic which has received considerable attention in the literature on empirical processes. The results are relevant as empirical norms occur due to symmetrization. They also play a prominent role in statistical applications. The contraction inequality has been a main tool but recently other approaches have shown to lead to better results in important cases. We present an overview including the linear (anisotropic) case, and give new results for inner products of functions. Our main application will be the estimation of the parental structure in a directed acyclic graph. As intermediate result we establish convergence of the least squares estimator when the model is wrong.

Recommendations

• Uniform consistency in causal inference
• scientific article; zbMATH DE number 4007348
• scientific article; zbMATH DE number 205878
• A uniformly consistent estimator of causal effects under the \(k\)-triangle-faithfulness assumption
• Some uniform convergence results for kernel estimators

Cites Work

• scientific article; zbMATH DE number 49190 (Why is no real title available?)
• scientific article; zbMATH DE number 1420699 (Why is no real title available?)
• A remark on low rank matrix recovery and noncommutative Bernstein type inequalities
• About the constants in Talagrand's concentration inequalities for empirical processes.
• Adaptive model selection using empirical complexities
• Aggregation via empirical risk minimization
• Atomic Decomposition by Basis Pursuit
• Bracketing metric entropy rates and empirical central limit theorems for function classes of Besov- and Sobolev-type
• Concentration inequalities and asymptotic results for ratio type empirical processes
• Concentration of measure and isoperimetric inequalities in product spaces
• Confidence sets in sparse regression
• Convergence of stochastic processes
• High-dimensional additive modeling
• High-dimensional regression with noisy and missing data: provable guarantees with nonconvexity
• Local Rademacher complexities
• On asymptotically optimal confidence regions and tests for high-dimensional models
• On sparse reconstruction from Fourier and Gaussian measurements
• On the conditions used to prove oracle results for the Lasso
• Penalized least squares estimation in the additive model with different smoothness for the components
• Reconstruction From Anisotropic Random Measurements
• Sharp bounds on the rate of convergence of the empirical covariance matrix
• Simultaneous analysis of Lasso and Dantzig selector
• Strong converse for identification via quantum channels
• Subspaces and orthogonal decompositions generated by bounded orthogonal systems
• The partial linear model in high dimensions
• The sizes of compact subsets of Hilbert space and continuity of Gaussian processes
• Weak convergence and empirical processes. With applications to statistics
• \(\ell _{1}\)-regularized linear regression: persistence and oracle inequalities
• \(\ell_{0}\)-penalized maximum likelihood for sparse directed acyclic graphs

Cited In (10)

• The partial linear model in high dimensions
• Greedy algorithms for prediction
• Minimax optimal estimation in partially linear additive models under high dimension
• On higher order isotropy conditions and lower bounds for sparse quadratic forms
• Additive models with trend filtering
• On the inference of applying Gaussian process modeling to a deterministic function
• CAM: causal additive models, high-dimensional order search and penalized regression
• Marginal integration for nonparametric causal inference
• Penalized least squares estimation in the additive model with different smoothness for the components
• Causal inference in partially linear structural equation models

Uses Software

• PDCO
• hgam

This page was built for publication: On the uniform convergence of empirical norms and inner products, with application to causal inference

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2452107)