High-dimensional probability. An introduction with applications in data science

DOI10.1017/9781108231596zbMATH Open1430.60005OpenAlexW4250954493MaRDI QIDQ4643248FDOQ4643248

Roman Vershynin

Publication date: 24 May 2018

Full work available at URL: https://doi.org/10.1017/9781108231596

Recommendations

• High-dimensional statistics. A non-asymptotic viewpoint
• Four lectures on probabilistic methods for data science
• scientific article
• Concentration inequalities. A nonasymptotic theory of independence
• An introduction to matrix concentration inequalities

zbMATH Keywords

clusteringcovariance estimationdata sciencedimension reductionmachine learninghigh dimensionsmatrix completionnetworkssemidefinite programmingempirical processescompressed sensingconcentration inequalitiessparse regressionVC dimensioncoding

Mathematics Subject Classification ID

Introductory exposition (textbooks, tutorial papers, etc.) pertaining to statistics (62-01) Introductory exposition (textbooks, tutorial papers, etc.) pertaining to probability theory (60-01)

Cited In (only showing first 100 items - show all)

• Adaptive sampling line search for local stochastic optimization with integer variables
• On sample average approximation for two-stage stochastic programs without relatively complete recourse
• Supervised learning of sheared distributions using linearized optimal transport
• Committor functions via tensor networks
• Model-free optimal control of discrete-time systems with additive and multiplicative noises
• Central limit theorem and bootstrap approximation in high dimensions: near \(1/\sqrt{n}\) rates via implicit smoothing
• Stable recovery of entangled weights: towards robust identification of deep neural networks from minimal samples
• The interpolation phase transition in neural networks: memorization and generalization under lazy training
• New challenges in covariance estimation: multiple structures and coarse quantization
• Asymptotic normality of robust \(M\)-estimators with convex penalty
• Covariance estimation under one-bit quantization
• Robust and resource-efficient identification of two hidden layer neural networks
• Complex phase retrieval from subgaussian measurements
• Crawling subsampling for multivariate spatial autoregression model in large-scale networks
• Concentration of kernel matrices with application to kernel spectral clustering
• Bootstrapping the operator norm in high dimensions: error estimation for covariance matrices and sketching
• Design of c-optimal experiments for high-dimensional linear models
• Suboptimality of constrained least squares and improvements via non-linear predictors
• Random zero sets for Fock type spaces
• Minimax optimality of permutation tests
• Uniform Hanson-Wright type concentration inequalities for unbounded entries via the entropy method
• Interacting diffusions on sparse graphs: hydrodynamics from local weak limits
• Title not available (Why is that?)
• Title not available (Why is that?)
• Uniform Bounds for Invariant Subspace Perturbations
• Two Models of Double Descent for Weak Features
• Statistical guarantees for regularized neural networks
• Title not available (Why is that?)
• Lasso Hyperinterpolation Over General Regions
• Outliers in spectrum of sparse Wigner matrices
• On Feasibility of Sample Average Approximation Solutions
• Reinforcement Learning for Linear-Convex Models with Jumps via Stability Analysis of Feedback Controls
• Holographic phase retrieval and reference design
• Fluctuations for the partition function of Ising models on Erdös-Rényi random graphs
• Topics and Techniques in Distribution Testing: A Biased but Representative Sample
• Deep learning: a statistical viewpoint
• A theory of capacity and sparse neural encoding
• Robust sensing of low-rank matrices with non-orthogonal sparse decomposition
• A deep network construction that adapts to intrinsic dimensionality beyond the domain
• Debiasing convex regularized estimators and interval estimation in linear models
• Thin-shell theory for rotationally invariant random simplices
• Gaussian discrepancy: a probabilistic relaxation of vector balancing
• Asymptotic distribution of the maximum interpoint distance for high-dimensional data
• Improved concentration bounds for sums of independent sub-exponential random variables
• Exact minimax risk for linear least squares, and the lower tail of sample covariance matrices
• Robust post-selection inference of high-dimensional mean regression with heavy-tailed asymmetric or heteroskedastic errors
• Online non-parametric changepoint detection with application to monitoring operational performance of network devices
• Optimal combination of linear and spectral estimators for generalized linear models
• High dimensional normality of noisy eigenvectors
• Consistency of invariance-based randomization tests
• Sharp optimal recovery in the two component Gaussian mixture model
• Model-free linear quadratic regulator
• Improved central limit theorem and bootstrap approximations in high dimensions
• Time-varying general dynamic factor models and the measurement of financial connectedness
• Temporal correlation in last passage percolation with flat initial condition via Brownian comparison
• The Lower Bound for Koldobsky’s Slicing Inequality via Random Rounding
• Bounding the expectation of the supremum of empirical processes indexed by Hölder classes
• Modified log-Sobolev inequalities and two-level concentration
• Title not available (Why is that?)
• On Polyhedral Approximations of the Positive Semidefinite Cone
• Improved Discrete Gaussian and Subgaussian Analysis for Lattice Cryptography
• Estimating covariance and precision matrices along subspaces
• A note on concentration for polynomials in the Ising model
• Species tree estimation under joint modeling of coalescence and duplication: sample complexity of quartet methods
• Norms of weighted sums of log-concave random vectors
• Title not available (Why is that?)
• Randomized Gram--Schmidt Process with Application to GMRES
• Generalized Low-Rank Plus Sparse Tensor Estimation by Fast Riemannian Optimization
• Non-convex exact community recovery in stochastic block model
• On recovery guarantees for one-bit compressed sensing on manifolds
• Guarantees for the Kronecker fast Johnson-Lindenstrauss transform using a coherence and sampling argument
• Title not available (Why is that?)
• SONIC: social network analysis with influencers and communities
• Hanson-Wright inequality in Banach spaces
• Rank-one multi-reference factor analysis
• Instability results for Euclidean distance, nearest neighbor search on high dimensional Gaussian data
• Robust Inference of Manifold Density and Geometry by Doubly Stochastic Scaling
• High dimensional decision making, upper and lower bounds
• Estimation of smooth functionals of location parameter in Gaussian and Poincaré random shift models.
• Finite impulse response models: a non-asymptotic analysis of the least squares estimator
• Nearly optimal robust mean estimation via empirical characteristic function
• Universality of approximate message passing algorithms
• Iteratively reweighted \(\ell_1\)-penalized robust regression
• Sparse random tensors: concentration, regularization and applications
• Polynomial Threshold Functions, Hyperplane Arrangements, and Random Tensors
• Randomized weakly admissible meshes
• Robust two-sample test of high-dimensional mean vectors under dependence
• Optimal rates of estimation for multi-reference alignment
• Robust inference via multiplier bootstrap
• Concentration inequalities for random tensors
• Lasso regression in sparse linear model with \(\varphi\)-mixing errors
• A simple approach for quantizing neural networks
• Inference on the change point under a high dimensional sparse mean shift
• On block Gaussian sketching for the Kaczmarz method
• Central limit theorem for peaks of a random permutation in a fixed conjugacy class of \(S_n\)
• Fast generalization error bound of deep learning without scale invariance of activation functions
• Endpoint Results for Fourier Integral Operators on Noncompact Symmetric Spaces
• Hanson-Wright inequality in Hilbert spaces with application to \(K\)-means clustering for non-Euclidean data
• Robust concentration inequalities in maximal exponential models
• \(\ell^1\)-analysis minimization and generalized (co-)sparsity: when does recovery succeed?

This page was built for publication: High-dimensional probability. An introduction with applications in data science

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4643248)