Geometric Inference for General High-Dimensional Linear Inverse Problems

Abstract

This paper presents a unified geometric framework for the statistical analysis of a general ill-posed linear inverse model which includes as special cases noisy compressed sensing, sign vector recovery, trace regression, orthogonal matrix estimation, and noisy matrix completion. We propose computationally feasible convex programs for statistical inference including estimation, confidence intervals and hypothesis testing. A theoretical framework is developed to characterize the local estimation rate of convergence and to provide statistical inference guarantees. Our results are built based on the local conic geometry and duality. The difficulty of statistical inference is captured by the geometric characterization of the local tangent cone through the Gaussian width and Sudakov minoration estimate.

39 pages, 6 figures

References in corpus (3)

• A new perspective on least squares under convex constraint
• Simple Bounds for Noisy Linear Inverse Problems with Exact Side Information
• Estimation in high dimensions: a geometric perspective

Cited by in corpus (7)

• Inference and Uncertainty Quantification for Noisy Matrix Completion
• Inference for Heterogeneous Effects using Low-Rank Estimation of Factor Slopes
• Optimal Structured Principal Subspace Estimation: Metric Entropy and Minimax Rates
• Consistent Risk Estimation in Moderately High-Dimensional Linear Regression
• Structured Matrix Recovery via the Generalized Dantzig Selector
• Confidence Region of Singular Subspaces for Low-rank Matrix Regression
• Linear signal recovery from $b$-bit-quantized linear measurements: precise analysis of the trade-off between bit depth and number of measurements