Sparse spectral estimation with missing and corrupted measurements

Supervised learning methods with missing data have been extensively studied not just due to the techniques related to low‐rank matrix completion. Also, in unsupervised learning, one often relies on imputation methods. As a matter of fact, missing values induce a bias in various estimators such as the sample covariance matrix. In the present paper, a convex method for sparse subspace estimation is extended to the case of missing and corrupted measurements. This is done by correcting the bias instead of imputing the missing values. The estimator is then used as an initial value for a nonconvex procedure to improve the overall statistical performance. The methodological and theoretical frameworks are applied to a wide range of statistical problems. These include sparse principal component analysis with different types of randomly missing data. Finally, the statistical performance is demonstrated on synthetic data.

• Publication year

  2018

• Venue

  Stat

• Publication date

  2018-11-26

• Fields of study

  Mathematics, Computer Science, Engineering

• Identifiers
  DOI 10.1002/sta4.229arXiv 1811.10443
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• Sparse principal component analysis with missing observations

  2019cited by this paper
• De-biased sparse PCA: Inference and testing for eigenstructure of large covariance matrices

  2018cited by this paper
• Sharp Oracle Inequalities for Stationary Points of Nonconvex Penalized M-Estimators

  2018cited by this paper
• Rate-Optimal Perturbation Bounds for Singular Subspaces with Applications to High-Dimensional Statistics

  2016cited by this paper
• missMDA: A Package for Handling Missing Values in Multivariate Data Analysis

  2016cited by this paper
• Estimation and Testing Under Sparsity: École d'Été de Probabilités de Saint-Flour XLV – 2015

  2016influential reference
• Minimax rate-optimal estimation of high-dimensional covariance matrices with incomplete data

  2016cited by this paper
• Ecole d'été de probabilités de Saint-Flour XLV

  2016influential reference
• Spectral thresholds in the bipartite stochastic block model

  2015cited by this paper
• Fantope Projection and Selection: A near-optimal convex relaxation of sparse PCA

  2013cited by this paper
• Minimax risk of matrix denoising by singular value thresholding

  2013cited by this paper
• Complexity Theoretic Lower Bounds for Sparse Principal Component Detection

  2013influential reference
• Sparse Principal Component Analysis with Missing Observations

  2012cited by this paper
• Optimal detection of sparse principal components in high dimension

  2012influential reference
• High-dimensional covariance matrix estimation with missing observations

  2012cited by this paper
• MINIMAX SPARSE PRINCIPAL SUBSPACE ESTIMATION IN HIGH DIMENSIONS

  2012cited by this paper
• The singular values and vectors of low rank perturbations of large rectangular random matrices

  2011influential reference
• High-dimensional regression with noisy and missing data: Provable guarantees with non-convexity

  2011influential reference
• Reconstruction of a low-rank matrix in the presence of Gaussian noise

  2010cited by this paper
• Spectral Regularization Algorithms for Learning Large Incomplete Matrices

  2010cited by this paper
• Nuclear norm penalization and optimal rates for noisy low rank matrix completion

  2010cited by this paper
• Matrix Completion from Noisy Entries

  2009cited by this paper
• Estimation of (near) low-rank matrices with noise and high-dimensional scaling

  2009cited by this paper
• On Consistency and Sparsity for Principal Components Analysis in High Dimensions

  2009cited by this paper
• The Power of Convex Relaxation: Near-Optimal Matrix Completion

  2009influential reference
• High-dimensional analysis of semidefinite relaxations for sparse principal components

  2008cited by this paper
• Exact Matrix Completion via Convex Optimization

  2008cited by this paper
• Measurement error in nonlinear models: a modern perspective

  2006cited by this paper
• Sparse Principal Component Analysis

  2006cited by this paper
• A Direct Formulation for Sparse PCA Using Semidefinite Programming

  2004cited by this paper
• Polynomial Regression and Estimating Functions in the Presence of Multiplicative Measurement Error

  1999cited by this paper
• Multiplicative Errors-in-Variables Models with Applications to Recent Data Released by the U.S. Department of Energy

  1986cited by this paper
• Analysis of a complex of statistical variables into principal components.

  1933cited by this paper
• LIII. On lines and planes of closest fit to systems of points in space

  1901cited by this paper

• High‐Dimensional Regression With Missing Data: An Asymptotic Study

  2025cites this paper
• Deep learning with missing data

  2025cites this paper
• Tests of missing completely at random based on sample covariance matrices

  2025cites this paper
• Nonparametric classification with missing data

  2024cites this paper
• Fisher information for smart sampling in time-domain spectroscopy.

  2024cites this paper
• An Adversarially Robust Formulation of Linear Regression With Missing Data

  2024cites this paper
• Covariance estimation under missing observations and L4−L2 moment equivalence

  2023cites this paper
• Fisher Information in Time-Domain Spectroscopy

  2023cites this paper
• Deflated HeteroPCA: Overcoming the curse of ill-conditioning in heteroskedastic PCA

  2023cites this paper
• Modular Regression: Improving Linear Models by Incorporating Auxiliary Data

  2022cites this paper
• Entrywise Recovery Guarantees for Sparse PCA via Sparsistent Algorithms

  2022cites this paper
• Optimal nonparametric testing of Missing Completely At Random and its connections to compatibility

  2022cites this paper
• RIGID: Robust Linear Regression with Missing Data

  2022cites this paper
• Subspace Estimation from Unbalanced and Incomplete Data Matrices: 𝓁2, ∞ Statistical Guarantees

  2021cites this paper
• Imputation for High-Dimensional Linear Regression

  2020cites this paper
• High‐dimensional principal component analysis with heterogeneous missingness

  2019cites this paper
• The correlation-assisted missing data estimator

  2019cites this paper
• O ct 2 01 9 Subspace Estimation from Unbalanced and Incomplete Data Matrices : l 2 , ∞ Statistical Guarantees

  2019cites this paper
• Subspace Estimation from Unbalanced and Incomplete Data Matrices: $\ell_{2,\infty}$ Statistical Guarantees.

  2019cites this paper