High-Dimensional Statistics

DOI10.1017/9781108627771zbMath1457.62011OpenAlexW4211030719MaRDI QIDQ4622691

Martin J. Wainwright

Publication date: 13 February 2019

Full work available at URL: https://doi.org/10.1017/9781108627771

zbMATH Keywords

principal component analysisrandom matricesHilbert spacesminimax lower boundgraphical modelshigh-dimensional statisticsnonparametric least squaresuniform laws of large numbers

Mathematics Subject Classification ID

Hypothesis testing in multivariate analysis (62H15) Random matrices (probabilistic aspects) (60B20) Learning and adaptive systems in artificial intelligence (68T05) Strong limit theorems (60F15) Research exposition (monographs, survey articles) pertaining to statistics (62-02) Hilbert spaces with reproducing kernels (= (proper) functional Hilbert spaces, including de Branges-Rovnyak and other structured spaces) (46E22) Empirical decision procedures; empirical Bayes procedures (62C12) Probabilistic graphical models (62H22) Statistical aspects of big data and data science (62R07)

Related Items

On Robustness of Principal Component Regression, Prediction Intervals for Synthetic Control Methods, Convergence guarantees for a class of non-convex and non-smooth optimization problems, Probing the Relationship Between Latent Linear Dynamical Systems and Low-Rank Recurrent Neural Network Models, Generalization Error Analysis of Neural Networks with Gradient Based Regularization, Learning Low-Dimensional Dynamical-System Models from Noisy Frequency-Response Data with Loewner Rational Interpolation, Binary Classification of Gaussian Mixtures: Abundance of Support Vectors, Benign Overfitting, and Regularization, Unnamed Item, Strong Embeddings for Transitory Queueing Models, Communication-Efficient Distributed Linear Discriminant Analysis for Binary Classification, High-dimensional dynamic systems identification with additional constraints, The inert drift atlas model, An Online Projection Estimator for Nonparametric Regression in Reproducing Kernel Hilbert Spaces, Optimal tail exponents in general last passage percolation via bootstrapping \& geodesic geometry, Learning Gaussian graphical models with latent confounders, Multiple change points detection in high-dimensional multivariate regression, Generalized linear models with structured sparsity estimators, Inducement of population sparsity, A semiparametric Bayesian approach to epidemics, with application to the spread of the coronavirus MERS in South Korea in 2015, Sampling numbers of smoothness classes via \(\ell^1\)-minimization, Towards Practical Large-Scale Randomized Iterative Least Squares Solvers through Uncertainty Quantification, Distributed Sparse Composite Quantile Regression in Ultrahigh Dimensions, An Algebraic Convergence Rate for the Optimal Control of McKean–Vlasov Dynamics, Inference for High-Dimensional Exchangeable Arrays, Generalized Liquid Association Analysis for Multimodal Data Integration, Distributed learning for sketched kernel regression, Functional regression with dependent error and missing observation in reproducing kernel Hilbert spaces, Sparse estimation in high-dimensional linear errors-in-variables regression via a covariate relaxation method, A framework of regularized low-rank matrix models for regression and classification, Proximinality and uniformly approximable sets in \(L^p\), Double bias correction for high-dimensional sparse additive hazards regression with covariate measurement errors, Estimating the effects of a California gun control program with multitask Gaussian processes, Controlling False Discovery Rate Using Gaussian Mirrors, Convergence Rates for Learning Linear Operators from Noisy Data, High-Dimensional Portfolio Selection with Cardinality Constraints, Global Rate Optimality of Integral Curve Estimators in High Order Tensor Models, Minimax rates for conditional density estimation via empirical entropy, User-friendly Introduction to PAC-Bayes Bounds, High-dimensional robust inference for censored linear models, Concentration inequalities for kernel density estimators under uniform mixing, Graphon mean-field control for cooperative multi-agent reinforcement learning, Orthogonal statistical learning, Optimal permutation estimation in crowdsourcing problems, Optimal Algorithms for Stochastic Complementary Composite Minimization, Generalized matrix decomposition regression: estimation and inference for two-way structured data, Affine statistical bundle modeled on a Gaussian Orlicz-Sobolev space, A communication efficient distributed one-step estimation, A historical overview of textbook presentations of statistical science, A convex-Nonconvex strategy for grouped variable selection, LASSO Reloaded: A Variational Analysis Perspective with Applications to Compressed Sensing, Optimal covariance matrix estimation for high-dimensional noise in high-frequency data, Retire: robust expectile regression in high dimensions, Reprint: Hypothesis testing on high dimensional quantile regression, Convergence Analysis of a Quasi-Monte CarloBased Deep Learning Algorithm for Solving Partial Differential Equations, Hypothesis testing on high dimensional quantile regression, Nonparametric Estimation of Repeated Densities with Heterogeneous Sample Sizes, Subspace Estimation with Automatic Dimension and Variable Selection in Sufficient Dimension Reduction, Fast randomized numerical rank estimation for numerically low-rank matrices, On the information complexity for integration in subspaces of the Wiener algebra, Bernstein-type bounds for beta distribution, A probabilistic view of latent space graphs and phase transitions, Minimax estimation of the mode of functional data, Change-point testing for parallel data sets with FDR control, Near-optimal bounds for generalized orthogonal Procrustes problem via generalized power method, A simple approach for quantizing neural networks, Optimally tackling covariate shift in RKHS-based nonparametric regression, A unified precision matrix estimation framework via sparse column-wise inverse operator under weak sparsity, Minimax rate of distribution estimation on unknown submanifolds under adversarial losses, Concentration of measure bounds for matrix-variate data with missing values, Non-asymptotic bounds for the \(\ell_{\infty}\) estimator in linear regression with uniform noise, Central limit theorems for high dimensional dependent data, Differentially private range query on shortest paths, An Asymptotic Analysis of Random Partition Based Minibatch Momentum Methods for Linear Regression Models, High‐dimensional limit theorems for SGD: Effective dynamics and critical scaling, Low-rank matrix estimation via nonconvex optimization methods in multi-response errors-in-variables regression, Robust high-dimensional tuning free multiple testing, Local Whittle estimation of high-dimensional long-run variance and precision matrices, High-dimensional composite quantile regression: optimal statistical guarantees and fast algorithms, Phase transition in noisy high-dimensional random geometric graphs, Sharper Bounds for Proximal Gradient Algorithms with Errors, Distributionally Favorable Optimization: A Framework for Data-Driven Decision-Making with Endogenous Outliers, Inference in a Class of Optimization Problems: Confidence Regions and Finite Sample Bounds on Errors in Coverage Probabilities, Unnamed Item, Matrix Factor Analysis: From Least Squares to Iterative Projection, Stability and optimization error of stochastic gradient descent for pairwise learning, High-Dimensional Probability: An Introduction with Applications in Data Science, Nonstationary Bandits with Habituation and Recovery Dynamics, Information Geometry of Smooth Densities on the Gaussian Space: Poincaré Inequalities, Unnamed Item, Unnamed Item, Unnamed Item, Is Temporal Difference Learning Optimal? An Instance-Dependent Analysis, Communication-Efficient Distributed Eigenspace Estimation, Unnamed Item, Unnamed Item, Unnamed Item, Unnamed Item, Unnamed Item, Towards Statistically Provable Geometric 3D Human Pose Recovery, Testing equality of several distributions in separable metric spaces: a maximum mean discrepancy based approach, Settling the sample complexity of model-based offline reinforcement learning, Supervised homogeneity fusion: a combinatorial approach, Confidence intervals of treatment effects in panel data models with interactive fixed effects, High-dimensional functional graphical model structure learning via neighborhood selection approach, Concentration of posterior model probabilities and normalized \({L_0}\) criteria, Fitting sparse linear models under the sufficient and necessary condition for model identification, Sparse Sliced Inverse Regression via Cholesky Matrix Penalization, \(\ell_0\)-regularized high-dimensional accelerated failure time model, Color Image Inpainting via Robust Pure Quaternion Matrix Completion: Error Bound and Weighted Loss, Generalization error of random feature and kernel methods: hypercontractivity and kernel matrix concentration, Metric entropy limits on recurrent neural network learning of linear dynamical systems, Bayesian hierarchical modeling: application towards production results in the Eagle Ford Shale of South Texas, Prediction theory for stationary functional time series, A general framework for tensor screening through smoothing, Inference in latent factor regression with clusterable features, Oracle lower bounds for stochastic gradient sampling algorithms, Empirical variance minimization with applications in variance reduction and optimal control, The asymptotic distribution of the MLE in high-dimensional logistic models: arbitrary covariance, An optimal uniform concentration inequality for discrete entropies on finite alphabets in the high-dimensional setting, Tail bounds for empirically standardized sums, Post-model-selection inference in linear regression models: an integrated review, Domains of attraction of invariant distributions of the infinite atlas model, Lower Bounds for Parallel and Randomized Convex Optimization, Fast nonasymptotic testing and support recovery for large sparse Toeplitz covariance matrices, Edge universality of correlated Gaussians, On two recent nonconvex penalties for regularization in machine learning, A data-driven line search rule for support recovery in high-dimensional data analysis, Interlacing and scaling exponents for the geodesic watermelon in last passage percolation, De-noising analysis of noisy data under mixed graphical models, On kernel methods for covariates that are rankings, Inadequacy of linear methods for minimal sensor placement and feature selection in nonlinear systems: a new approach using secants, Concentration of kernel matrices with application to kernel spectral clustering, Robust concentration inequalities in maximal exponential models, How can we identify the sparsity structure pattern of high-dimensional data: an elementary statistical analysis to interpretable machine learning, Gaussian concentration and uniqueness of equilibrium states in lattice systems, A convex optimization framework for the identification of homogeneous reaction systems, Differentially private SGD with non-smooth losses, Consistency and asymptotic normality of latent block model estimators, On randomized trace estimates for indefinite matrices with an application to determinants, Generic error bounds for the generalized Lasso with sub-exponential data, Time-uniform Chernoff bounds via nonnegative supermartingales, A sharp upper bound for sampling numbers in \(L_2\), Resource aware pricing for electric vehicle charging, Smoothed quantile regression with large-scale inference, On the sample complexity of the linear quadratic regulator, Double-estimation-friendly inference for high-dimensional misspecified models, Worst-case versus average-case design for estimation from partial pairwise comparisons, Linear regression with partially mismatched data: local search with theoretical guarantees, From Gauss to Kolmogorov: localized measures of complexity for ellipses, Wavelet eigenvalue regression in high dimensions, Staying the course: iteratively locating equilibria of dynamical systems on Riemannian manifolds defined by point-clouds, Greedy training algorithms for neural networks and applications to PDEs, Random walks on hyperbolic spaces: second order expansion of the rate function at the drift, Hanson-Wright inequality in Hilbert spaces with application to \(K\)-means clustering for non-Euclidean data, Discussion of ``Best subset, forward stepwise or Lasso? Analysis and recommendations based on extensive comparisons, Spectrally-truncated kernel ridge regression and its free lunch, Finite sample performance of linear least squares estimation, Exponential tail bounds for chisquared random variables, Bayesian model selection for high-dimensional Ising models, with applications to educational data, A goodness-of-fit test based on neural network sieve estimators, On concentration inequalities for vector-valued Lipschitz functions, Singularity, misspecification and the convergence rate of EM, A note on new Bernstein-type inequalities for the log-likelihood function of Bernoulli variables, A Note on Online Change Point Detection, Low-complexity learning of linear quadratic regulators from noisy data, Regression in Tensor Product Spaces by the Method of Sieves, Lasso estimation for spherical autoregressive processes, Instability results for Euclidean distance, nearest neighbor search on high dimensional Gaussian data, Tracy-Widom distribution, Airy\(_2\) process and its sample path properties, Relative utility bounds for empirically optimal portfolios, Graphical-model based high dimensional generalized linear models, Iteratively reweighted \(\ell_1\)-penalized robust regression, Concentration Inequalities for Statistical Inference, High-dimensional linear models: a random matrix perspective, Concentration bounds for temporal difference learning with linear function approximation: the case of batch data and uniform sampling, Variable selection consistency of Gaussian process regression, The cost of privacy: optimal rates of convergence for parameter estimation with differential privacy, Optimal model averaging estimator for expectile regressions, Non-uniform packings, Linear regression with mismatched data: a provably optimal local search algorithm, Compound Poisson point processes, concentration and oracle inequalities, Oracle inequalities for weighted group Lasso in high-dimensional misspecified Cox models, Superquantiles at work: machine learning applications and efficient subgradient computation, On strong consistency of kernel \(k\)-means: a Rademacher complexity approach, Provable training set debugging for linear regression, Regret lower bound and optimal algorithm for high-dimensional contextual linear bandit, High-dimensional inference for linear model with correlated errors, The foundations of statistical science: a history of textbook presentations, Error bounds of the invariant statistics in machine learning of ergodic Itô diffusions, Projected spline estimation of the nonparametric function in high-dimensional partially linear models for massive data, Online non-parametric changepoint detection with application to monitoring operational performance of network devices, Random graph asymptotics for treatment effect estimation under network interference, Probabilistic Guarantees in Robust Optimization, GenMod: a generative modeling approach for spectral representation of PDEs with random inputs, Out-of-Sample Utility Bounds for Empirically Optimal Portfolios in a Single-Period Investment Problem, A sieve stochastic gradient descent estimator for online nonparametric regression in Sobolev ellipsoids, Adaptive Bayesian inference for current status data on a grid, Suboptimality of constrained least squares and improvements via non-linear predictors, A Lecture About the Use of Orlicz Spaces in Information Geometry, From inexact optimization to learning via gradient concentration, Minimax rate for optimal transport regression between distributions, Optimization hierarchy for fair statistical decision problems, Toward theoretical understandings of robust Markov decision processes: sample complexity and asymptotics, A Theoretical Perspective on Hyperdimensional Computing, Low rank matrix recovery with adversarial sparse noise*