Gaussian approximations and multiplier bootstrap for maxima of sums of high-dimensional random vectors
From MaRDI portal
Publication:2443203
Abstract: We derive a Gaussian approximation result for the maximum of a sum of high-dimensional random vectors. Specifically, we establish conditions under which the distribution of the maximum is approximated by that of the maximum of a sum of the Gaussian random vectors with the same covariance matrices as the original vectors. This result applies when the dimension of random vectors () is large compared to the sample size (); in fact, can be much larger than , without restricting correlations of the coordinates of these vectors. We also show that the distribution of the maximum of a sum of the random vectors with unknown covariance matrices can be consistently estimated by the distribution of the maximum of a sum of the conditional Gaussian random vectors obtained by multiplying the original vectors with i.i.d. Gaussian multipliers. This is the Gaussian multiplier (or wild) bootstrap procedure. Here too, can be large or even much larger than . These distributional approximations, either Gaussian or conditional Gaussian, yield a high-quality approximation to the distribution of the original maximum, often with approximation error decreasing polynomially in the sample size, and hence are of interest in many applications. We demonstrate how our Gaussian approximations and the multiplier bootstrap can be used for modern high-dimensional estimation, multiple hypothesis testing, and adaptive specification testing. All these results contain nonasymptotic bounds on approximation errors.
Recommendations
- Central limit theorems and bootstrap in high dimensions
- Beyond Gaussian approximation: bootstrap for maxima of sums of independent random vectors
- Gaussian approximations for maxima of random vectors under \((2+\iota)\)-th moments
- Gaussian and bootstrap approximations for high-dimensional U-statistics and their applications
- Bootstrapping max statistics in high dimensions: near-parametric rates under weak variance decay and application to functional and multinomial data
Cites work
- scientific article; zbMATH DE number 1952026 (Why is no real title available?)
- A user's guide to measure theoretic probability
- An approximation of partial sums of independent RV'-s, and the sample DF. I
- Bootstrap and wild bootstrap for high dimensional linear models
- Comparison and anti-concentration bounds for maxima of Gaussian random vectors
- Confidence bands in density estimation
- Estimation of the mean of a multivariate normal distribution
- Exact and Approximate Stepdown Methods for Multiple Hypothesis Testing
- Exchangeably weighted bootstraps of the general empirical process
- Extremes and related properties of random sequences and processes
- Gaussian approximation of suprema of empirical processes
- Gaussian approximations and multiplier bootstrap for maxima of sums of high-dimensional random vectors
- Generalization of constraints for high dimensional regression problems
- Hungarian constructions from the nonasymptotic viewpoint
- Komlós-Major-Tusnády approximation for the general empirical process and Haar expansions of classes of functions
- Least squares after model selection in high-dimensional sparse models
- Local invariance principles and their application to density estimation
- Multiple Inference and Gender Differences in the Effects of Early Intervention: A Reevaluation of the Abecedarian, Perry Preschool, and Early Training Projects
- Multiscale testing of qualitative hypotheses
- Normal Approximation by Stein’s Method
- On parameters of increasing dimensions
- On verifiable sufficient conditions for sparse signal recovery via \(\ell_{1}\) minimization
- Rate minimaxity of the Lasso and Dantzig selector for the \(l_{q}\) loss in \(l_{r}\) balls
- Self-Normalized Processes
- Shape-constrained regularization by statistical multiresolution for inverse problems: asymptotic analysis
- Simultaneous analysis of Lasso and Dantzig selector
- Statistics for high-dimensional data. Methods, theory and applications.
- Stein's method in high dimensions with applications
- The Dantzig selector and sparsity oracle inequalities
- The Dantzig selector: statistical estimation when \(p\) is much larger than \(n\). (With discussions and rejoinder).
- The Sherrington-Kirkpatrick model
- To How Many Simultaneous Hypothesis Tests Can Normal, Student'stor Bootstrap Calibration Be Applied?
- Uniform Central Limit Theorems
- Weak convergence and empirical processes. With applications to statistics
Cited in
(only showing first 100 items - show all)- Notes on the dimension dependence in high-dimensional central limit theorems for hyperrectangles
- Maximum-type tests for high-dimensional regression coefficients using Wilcoxon scores
- Inference for High-Dimensional Exchangeable Arrays
- Large-Scale Inference of Multivariate Regression for Heavy-Tailed and Asymmetric Data
- Identifying the number of factors using a white noise test
- Change-point detection in high-dimensional covariance structure
- Are discoveries spurious? Distributions of maximum spurious correlations and their applications
- Central limit theorem in high dimensions: the optimal bound on dimension growth rate
- Joint test for homogeneity of high-dimensional means and covariance matrices using maximum-type statistics
- Gaussian approximation for high dimensional vector under physical dependence
- Adaptive Inference for Change Points in High-Dimensional Data
- Central limit theorem and bootstrap approximation in high dimensions: near \(1/\sqrt{n}\) rates via implicit smoothing
- New Edgeworth-type expansions with finite sample guarantees
- Relevant change points in high dimensional time series
- High-dimensional two-sample mean vectors test and support recovery with factor adjustment
- Two sample tests for high-dimensional autocovariances
- A sharp lower-tail bound for Gaussian maxima with application to bootstrap methods in high dimensions
- Non-integrable stable approximation by Stein's method
- On empirical distribution function of high-dimensional Gaussian vector components with an application to multiple testing
- Hypothesis testing for high-dimensional time series via self-normalization
- Jackknife multiplier bootstrap: finite sample approximations to the \(U\)-process supremum with applications
- A tuning-free efficient test for marginal linear effects in high-dimensional quantile regression
- Bootstrap consistency for quadratic forms of sample averages with increasing dimension
- Nonclassical Berry-Esseen inequalities and accuracy of the bootstrap
- Are Latent Factor Regression and Sparse Regression Adequate?
- Combinatorial inference for graphical models
- High-Dimensional MANOVA Via Bootstrapping and Its Application to Functional and Sparse Count Data
- Integrative Factor Regression and Its Inference for Multimodal Data Analysis
- Bootstrapping the operator norm in high dimensions: error estimation for covariance matrices and sketching
- Statistical Inferences for Complex Dependence of Multimodal Imaging Data
- Familywise error rate control via knockoffs
- Cauchy Combination Test: A Powerful Test With Analytic p-Value Calculation Under Arbitrary Dependency Structures
- On the use of bootstrap with variational inference: theory, interpretation, and a two-sample test example
- Bootstrap confidence sets under model misspecification
- Multiscale adaptive inference on conditional moment inequalities
- Central limit theorems and bootstrap in high dimensions
- Post-selection Inference of High-dimensional Logistic Regression Under Case–Control Design
- Inference on the best policies with many covariates
- Bootstrapping and sample splitting for high-dimensional, assumption-lean inference
- A bootstrap method for error estimation in randomized matrix multiplication
- Gaussian and bootstrap approximations for high-dimensional U-statistics and their applications
- On some approximations for sums of \(m\)-dependent random variables
- A multivariate Berry-Esseen theorem with explicit constants
- scientific article; zbMATH DE number 6443076 (Why is no real title available?)
- Comparison and anti-concentration bounds for maxima of Gaussian random vectors
- A remark on moment-dependent phase transitions in high-dimensional Gaussian approximations
- Multiscale change point detection
- Testing independence in high dimensions with sums of rank correlations
- Detection of multiple change-points in high-dimensional panel data with cross-sectional and temporal dependence
- Multi-sample hypothesis testing of high-dimensional mean vectors under covariance heterogeneity
- Distributed testing and estimation under sparse high dimensional models
- High-dimensional central limit theorems by Stein's method
- Uniformly valid post-regularization confidence regions for many functional parameters in z-estimation framework
- Simultaneous inference for pairwise graphical models with generalized score matching
- Nonparametric inference via bootstrapping the debiased estimator
- Gaussian approximations and multiplier bootstrap for maxima of sums of high-dimensional random vectors
- (Consistently) testing strict exogeneity against the alternative of predeterminedness in linear time-series models
- Gaussian approximations in high dimensional estimation
- Nonparametric inference in generalized functional linear models
- Beyond Gaussian approximation: bootstrap for maxima of sums of independent random vectors
- On the post selection inference constant under restricted isometry properties
- Convergence rates of least squares regression estimators with heavy-tailed errors
- Approximation to stochastic variance reduced gradient Langevin dynamics by stochastic delay differential equations
- Large-dimensional central limit theorem with fourth-moment error bounds on convex sets and balls
- Multiplier subsample bootstrap for statistics of time series
- On frequentist coverage errors of Bayesian credible sets in moderately high dimensions
- Estimating and inferring the maximum degree of stimulus‐locked time‐varying brain connectivity networks
- Gaussian Approximation and Spatially Dependent Wild Bootstrap for High-Dimensional Spatial Data
- A massive data framework for M-estimators with cubic-rate
- Controlling the familywise error rate when performing multiple comparisons in a linear latent variable model
- Bootstrapping max statistics in high dimensions: near-parametric rates under weak variance decay and application to functional and multinomial data
- High-dimensional CLT: improvements, non-uniform extensions and large deviations
- Cross-validation with confidence
- Covariance-based sample selection for heterogeneous data: applications to gene expression and autism risk gene detection
- Berry-Esseen bounds for Chernoff-type nonstandard asymptotics in isotonic regression
- Bounding the difference between true and nominal rejection probabilities in tests of hypotheses about instrumental variables models
- A max-correlation white noise test for weakly dependent time series
- A high-dimensional CLT in \(\mathcal {W}_2\) distance with near optimal convergence rate
- Nonparametric inference on Lévy measures of compound Poisson-driven Ornstein-Uhlenbeck processes under macroscopic discrete observations
- Inference on Multi-level Partial Correlations Based on Multi-subject Time Series Data
- A partially linear framework for massive heterogeneous data
- Estimating Orthant Probabilities of High-Dimensional Gaussian Vectors with An Application to Set Estimation
- Gaussian approximation of maxima of Wiener functionals and its application to high-frequency data
- Adaptive tests of conditional moment inequalities
- Improved convergence rates of normal extremes
- Estimation and inference in a high-dimensional semiparametric Gaussian copula vector autoregressive model
- A stationary bootstrap test about two mean vectors comparison with somewhat dense differences and fewer sample size than dimension
- Bootstrap Adjustment to Minimum p-Value Method for Predictive Classification
- Central limit theorem and near classical Berry-Esseen rate for self normalized sums in high dimensions
- Central limit theorems for high dimensional dependent data
- On some approximations for sums of independent random variables
- Partial recovery for top-\(k\) ranking: optimality of MLE and suboptimality of the spectral method
- Ridge regression revisited: debiasing, thresholding and bootstrap
- Testing the martingale difference hypothesis in high dimension
- A Berry-Esseen bound for vector-valued martingales
- Test of conditional independence in factor models via Hilbert-Schmidt independence criterion
- Inference on heterogeneous treatment effects in high‐dimensional dynamic panels under weak dependence
- Sharp high-dimensional central limit theorems for log-concave distributions
- Testing Mediation Effects Using Logic of Boolean Matrices
- The CLT in high dimensions: quantitative bounds via martingale embedding
This page was built for publication: Gaussian approximations and multiplier bootstrap for maxima of sums of high-dimensional random vectors
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2443203)
