An Introduction to Matrix Concentration Inequalities
From MaRDI portal
Publication:5499661
DOI10.1561/2200000048zbMath1391.15071arXiv1501.01571OpenAlexW4206039841WikidataQ94751518 ScholiaQ94751518MaRDI QIDQ5499661
Publication date: 30 July 2015
Published in: Foundations and Trends® in Machine Learning (Search for Journal in Brave)
Full work available at URL: https://arxiv.org/abs/1501.01571
Miscellaneous inequalities involving matrices (15A45) Random matrices (algebraic aspects) (15B52) Research exposition (monographs, survey articles) pertaining to linear algebra (15-02)
Related Items
Adaptive estimation of the copula correlation matrix for semiparametric elliptical copulas, Derandomized compressed sensing with nonuniform guarantees for \(\ell_1\) recovery, Convergence analysis of Oja's iteration for solving online PCA with nonzero-mean samples, The dimension-free structure of nonhomogeneous random matrices, On Azuma-type inequalities for Banach space-valued martingales, Functional principal subspace sampling for large scale functional data analysis, A Hoeffding inequality for Markov chains, A theoretical and empirical comparison of gradient approximations in derivative-free optimization, Partial recovery for top-\(k\) ranking: optimality of MLE and suboptimality of the spectral method, Norms of randomized circulant matrices, Ritz-like values in steplength selections for stochastic gradient methods, Far-field compression for fast kernel summation methods in high dimensions, Quantum concentration inequalities, Phase retrieval by binary questions: which complementary subspace is closer?, Unnamed Item, Unnamed Item, Identification of linear systems with multiplicative noise from multiple trajectory data, Asymmetry helps: eigenvalue and eigenvector analyses of asymmetrically perturbed low-rank matrices, On an unsupervised method for parameter selection for the elastic net, Improved Bounds for Small-Sample Estimation, Differentially private high dimensional sparse covariance matrix estimation, A randomized approach to sensor placement with observability assurance, Concentration of the spectral norm of Erdős-Rényi random graphs, Optimal rates of estimation for multi-reference alignment, Randomized matrix-free trace and log-determinant estimators, Distribution of singular values of random band matrices; Marchenko-Pastur law and more, Tensor Bernstein concentration inequalities with an application to sample estimators for high-order moments, A sketched finite element method for elliptic models, Generalizing Lieb's concavity theorem via operator interpolation, A Probabilistic Subspace Bound with Application to Active Subspaces, Norms of random matrices: local and global problems, Time-uniform Chernoff bounds via nonnegative supermartingales, Implicit regularization in nonconvex statistical estimation: gradient descent converges linearly for phase retrieval, matrix completion, and blind deconvolution, Optimization based methods for partially observed chaotic systems, The Expected Norm of a Sum of Independent Random Matrices: An Elementary Approach, Unnamed Item, Unnamed Item, Unnamed Item, Unnamed Item, Unnamed Item, Robust covariance estimation under \(L_4\)-\(L_2\) norm equivalence, Risk bounds when learning infinitely many response functions by ordinary linear regression, Spectral norm bounds for block Markov chain random matrices, Tensor sparsification via a bound on the spectral norm of random tensors: Algorithm 1., Time for dithering: fast and quantized random embeddings via the restricted isometry property, Laguerre deconvolution with unknown matrix operator, Applied harmonic analysis and data science. Abstracts from the workshop held November 28 -- December 4, 2021 (hybrid meeting), Generalization bounds for learning weighted automata, Newton-type methods for non-convex optimization under inexact Hessian information, Hurwitz and the origins of random matrix theory in mathematics, MSE bounds for estimators of matrix functions, Spectral clustering in the dynamic stochastic block model, Reduced rank regression with matrix projections for high-dimensional multivariate linear regression model, Some new asymptotic theory for least squares series: pointwise and uniform results, Near-optimality of linear recovery from indirect observations, Kernel conjugate gradient methods with random projections, Sublinear-Time Quadratic Minimization via Spectral Decomposition of Matrices, Semidefinite approximations of the matrix logarithm, Second-order matrix concentration inequalities, Real-valued embeddings and sketches for fast distance and similarity estimation, Simplicial faces of the set of correlation matrices, Sub-Gaussian estimators of the mean of a random matrix with heavy-tailed entries, Random Laplacian matrices and convex relaxations, Clustering in block Markov chains, Statistical inference on random dot product graphs: a survey, A generalized Lieb's theorem and its applications to spectrum estimates for a sum of random matrices, Unnamed Item, Unnamed Item, Drift estimation on non compact support for diffusion models, Moment inequalities for matrix-valued U-statistics of order 2, Low-rank matrix completion in a general non-orthogonal basis, Time-uniform, nonparametric, nonasymptotic confidence sequences, From Poincaré inequalities to nonlinear matrix concentration, Convex optimization for the densest subgraph and densest submatrix problems, Non-asymptotic results for singular values of Gaussian matrix products, Nonlinear matrix concentration via semigroup methods, Convergence analysis of a collapsed Gibbs sampler for Bayesian vector autoregressions, Nyström subsampling method for coefficient-based regularized regression, Sensor calibration for off-the-grid spectral estimation, Regression function estimation on non compact support in an heteroscesdastic model, Sharp oracle inequalities for low-complexity priors, Randomized linear algebra for model reduction. I. Galerkin methods and error estimation, Control variate selection for Monte Carlo integration, Concentration inequalities for random matrix products, The spectral norm of random lifts of matrices, Exact recovery in the Ising blockmodel, Spectral method and regularized MLE are both optimal for top-\(K\) ranking, Randomized signal processing with continuous frames, Analysis of spectral clustering algorithms for community detection: the general bipartite setting, Matrix Poincaré inequalities and concentration, Spectral Analysis of Matrix Scaling and Operator Scaling, An approximation algorithm for the maximum spectral subgraph problem, Linesearch Newton-CG methods for convex optimization with noise, Mixing time estimation in reversible Markov chains from a single sample path, Moment bounds for large autocovariance matrices under dependence, Constructive regularization of the random matrix norm, Optimal rates for coefficient-based regularized regression, Unnamed Item, Matrix concentration for products, Suboptimality of constrained least squares and improvements via non-linear predictors, Stochastic analysis of an adaptive cubic regularization method under inexact gradient evaluations and dynamic Hessian accuracy, Monte Carlo Methods for Estimating the Diagonal of a Real Symmetric Matrix, Stationary Density Estimation of Itô Diffusions Using Deep Learning, Randomized numerical linear algebra: Foundations and algorithms, Color Image Inpainting via Robust Pure Quaternion Matrix Completion: Error Bound and Weighted Loss, Schwinger–Dyson and loop equations for a product of square Ginibre random matrices, Nonstationary Modeling With Sparsity for Spatial Data via the Basis Graphical Lasso, Unnamed Item, Semi-Infinite Linear Regression and Its Applications, Convexification with Bounded Gap for Randomly Projected Quadratic Optimization, A Theory of Quantum Subspace Diagonalization, Joint Community Detection and Rotational Synchronization via Semidefinite Programming, An adaptive stochastic sequential quadratic programming with differentiable exact augmented Lagrangians, Generative modeling via tree tensor network states, Inequality constrained stochastic nonlinear optimization via active-set sequential quadratic programming, Matrix concentration inequalities and free probability, Distributed learning for sketched kernel regression, Multifidelity Dimension Reduction via Active Subspaces, Stochastic Gauss-Newton algorithms for online PCA, Tight computationally efficient approximation of matrix norms with applications, Spectral analysis of the quantum random energy model, Improved estimation of relaxation time in nonreversible Markov chains, Norms of structured random matrices, Analysis of a Computational Framework for Bayesian Inverse Problems: Ensemble Kalman Updates and MAP Estimators under Mesh Refinement, Faster Riemannian Newton-type optimization by subsampling and cubic regularization, Phase Retrieval by Linear Algebra, Spectral methods for solving elliptic PDEs on unknown manifolds, Random geometric graph: some recent developments and perspectives, Spectrahedral Regression, High-dimensional estimation of quadratic variation based on penalized realized variance, A Spectral Method for Joint Community Detection and Orthogonal Group Synchronization, Compression and data similarity: combination of two techniques for communication-efficient solving of distributed variational inequalities, Assigning topics to documents by successive projections, Reweighted nonparametric likelihood inference for linear functionals, Average-case speedup for product formulas, Sample Size Estimates for Risk-Neutral Semilinear PDE-Constrained Optimization, Online Decision Making with High-Dimensional Covariates, Matrix Poincaré, Φ-Sobolev inequalities, and quantum ensembles, Unnamed Item, A Stochastic Line Search Method with Expected Complexity Analysis, Distributed learning with indefinite kernels, Nonparametric survival function estimation for data subject to interval censoring case 2, Adaptive Regularization Algorithms with Inexact Evaluations for Nonconvex Optimization, Unnamed Item, Unnamed Item, Unnamed Item, Best Low-rank Approximations and Kolmogorov $n$-widths, Matching Component Analysis for Transfer Learning
