Statistical Inferences of Linear Forms for Noisy Matrix Completion

Abstract

We introduce a flexible framework for making inferences about general linear forms of a large matrix based on noisy observations of a subset of its entries. In particular, under mild regularity conditions, we develop a universal procedure to construct asymptotically normal estimators of its linear forms through double-sample debiasing and low-rank projection whenever an entry-wise consistent estimator of the matrix is available. These estimators allow us to subsequently construct confidence intervals for and test hypotheses about the linear forms. Our proposal was motivated by a careful perturbation analysis of the empirical singular spaces under the noisy matrix completion model which might be of independent interest. The practical merits of our proposed inference procedure are demonstrated on both simulated and real-world data examples.

arXiv commentMinor typos are corrected; real data examples are added

References in corpus (15)

• Guaranteed Minimum-Rank Solutions of Linear Matrix Equations via Nuclear Norm Minimization
• Confidence Intervals and Hypothesis Testing for High-Dimensional Regression
• Estimation of high-dimensional low-rank matrices
• Implicit Regularization in Nonconvex Statistical Estimation: Gradient Descent Converges Linearly for Phase Retrieval, Matrix Completion, and Blind Deconvolution
• Fast low-rank estimation by projected gradient descent: General statistical and algorithmic guarantees
• Convergence Analysis for Rectangular Matrix Completion Using Burer-Monteiro Factorization and Gradient Descent
• Matrix Completion via Max-Norm Constrained Optimization
• Optimal Estimation and Completion of Matrices with Biclustering Structures
• Universal low-rank matrix recovery from Pauli measurements
• The Power of Convex Relaxation: Near-Optimal Matrix Completion
• Uncertainty Quantification for Matrix Compressed Sensing and Quantum Tomography Problems
• Noisy Matrix Completion: Understanding Statistical Guarantees for Convex Relaxation via Nonconvex Optimization
• On Polynomial Time Methods for Exact Low Rank Tensor Completion
• A Unified Computational and Statistical Framework for Nonconvex Low-Rank Matrix Estimation
• Nonconvex Rectangular Matrix Completion via Gradient Descent without ${\ell }_{2,\infty }$ Regularization

Cited by in corpus (4)

• Recent Developments on Factor Models and its Applications in Econometric Learning
• A Note on Exploratory Item Factor Analysis by Singular Value Decomposition
• Minimax Estimation of Linear Functions of Eigenvectors in the Face of Small Eigen-Gaps
• Unfolding-Model-Based Visualization: Theory, Method and Applications