Spectral Methods for Data Science: A Statistical Perspective

DOI10.1561/2200000079MaRDI QIDQ5015834zbMATH OpenOpenAlexFDO

Authors Yuxin Chen, Yuejie Chi, Cong Ma, Jianqing Fan

Publication date 9 December 2021

Published in Foundations and Trends® in Machine Learning (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/2012.08496

zbMATH Keywords

clusteringoperations researchspectral methodssignal reconstructionsparse representationsstatistical learning theorymetasearchclassification and predictionstatistical/machine learningcollaborative filtering and recommender systemsinformation theory and statisticslearning and statistical methodspattern recognition and learningrank aggregation and data fusion

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Research exposition (monographs, survey articles) pertaining to computer science (68-02)

Recommendations

• Spectral algorithms
• Spectral methods for matrices and tensors
• Subspace estimation from unbalanced and incomplete data matrices: \({\ell_{2,\infty}}\) statistical guarantees
• scientific article; zbMATH DE number 7049740
• Entrywise eigenvector analysis of random matrices with low expected rank

Cited in

(62)

• Testing sufficiency for transfer learning
• Finding mixed memberships in categorical data
• Self-supervised Metric Learning in Multi-View Data: A Downstream Task Perspective
• Asymptotic limits of spiked eigenvalues and eigenvectors of signal-plus-noise matrices with weak signals and heteroskedastic noise
• Uniform error bound for PCA matrix denoising
• Fast gradient method for low-rank matrix estimation
• Generative modeling via tree tensor network states
• Network-adjusted covariates for community detection
• Deflated HeteroPCA: overcoming the curse of ill-conditioning in heteroskedastic PCA
• A spectral method for identifiable grade of membership analysis with binary responses
• Generative modeling via tensor train sketching
• Optimal spectral recovery of a planted vector in a subspace
• Analysis of singular subspaces under random perturbations
• Spectrum-aware debiasing: a modern inference framework with applications to principal components regression
• Robust high-dimensional tuning free multiple testing
• Robust Recovery of Low-Rank Matrices and Low-Tubal-Rank Tensors from Noisy Sketches
• Discussion of: ``Statistical exploration of the manifold hypothesis
• Discussion of: ``Statistical exploration of the manifold hypothesis
• Discussion of: ``Statistical exploration of the manifold hypothesis
• Discussion of: ``Statistical exploration of the manifold hypothesis
• Discussion of: ``Statistical exploration of the manifold hypothesis
• Discussion of: ``Statistical exploration of the manifold hypothesis
• Discussion of: ``Statistical exploration of the manifold hypothesis
• Discussion of: ``Statistical exploration of the manifold hypothesis
• Discussion of: ``Statistical exploration of the manifold hypothesis
• Discussion of: ``Statistical exploration of the manifold hypothesis
• Discussion of: ``Statistical exploration of the manifold hypothesis
• Discussion of: ``Statistical exploration of the manifold hypothesis
• Discussion of: ``Statistical exploration of the manifold hypothesis
• Discussion of: ``Statistical exploration of the manifold hypothesis
• Discussion of: ``Statistical exploration of the manifold hypothesis
• Discussion of: ``Statistical exploration of the manifold hypothesis
• Discussion of: ``Statistical exploration of the manifold hypothesis
• Discussion of: ``Statistical exploration of the manifold hypothesis
• Discussion of: ``Statistical exploration of the manifold hypothesis
• Discussion of: ``Statistical exploration of the manifold hypothesis
• Discussion of: ``Statistical exploration of the manifold hypothesis
• Discussion of: ``Statistical exploration of the manifold hypothesis
• Discussion of: ``Statistical exploration of the manifold hypothesis
• Discussion of: ``Statistical exploration of the manifold hypothesis
• Discussion of: ``Statistical exploration of the manifold hypothesis
• Discussion of: ``Statistical exploration of the manifold hypothesis
• Discussion of: ``Statistical exploration of the manifold hypothesis
• Discussion of: ``Statistical exploration of the manifold hypothesis
• Discussion of: ``Statistical exploration of the manifold hypothesis
• Discussion of: ``Statistical exploration of the manifold hypothesis
• Discussion of: ``Statistical exploration of the manifold hypothesis
• Reply to the discussion of: ``Statistical exploration of the manifold hypothesis
• Learning low-dimensional nonlinear structures from high-dimensional noisy data: an integral operator approach
• The power of preconditioning in overparameterized low-rank matrix sensing
• Statistical ranking with dynamic covariates
• Robust two-way dimension reduction by Grassmannian barycenter
• Partial recovery and weak consistency in the non-uniform hypergraph stochastic block model
• Learning from similar linear representations: adaptivity, minimaxity, and robustness
• Structured matrix learning under arbitrary entrywise dependence and estimation of Markov transition kernel
• Data denoising with self-consistency, variance maximization, and the Kantorovich dominance
• Testing for latent structure via the Wilcoxon-Wigner random matrix of normalized rank statistics
• Spectral estimators for structured generalized linear models via approximate message passing
• Randomized spectral clustering for large-scale multi-layer networks
• Mixed membership estimation for categorical data with weighted responses
• Higher-order entrywise eigenvectors analysis of low-rank random matrices: bias correction, Edgeworth expansion and bootstrap
• Efficient estimation of the central mean subspace via smoothed gradient outer products

This page was built for publication: Spectral Methods for Data Science: A Statistical Perspective

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5015834)