Inference and uncertainty quantification for noisy matrix completion

Abstract

Matrix completion finds numerous applications in data science, ranging from information retrieval to medical imaging. While substantial progress has been made in designing estimation algorithms, it remains unknown how to perform optimal statistical inference on the unknown matrix given the obtained estimates—a task at the core of modern decision making. We propose procedures to debias the popular convex and nonconvex estimators and derive distributional characterizations for the resulting debiased estimators. This distributional theory enables valid inference on the unknown matrix. Our procedures 1) yield optimal construction of confidence intervals for missing entries and 2) achieve optimal estimation accuracy in a sharp manner.

Document Details

Document Type
Pub Defense Publication
Publication Date
Oct 30, 2019
Source ID
10.1073/pnas.1910053116

Entities

People

  • Cong Ma
  • Jianqing Fan
  • Yuling Yan
  • Yuxin Chen

Organizations

  • Air Force Office of Scientific Research
  • Army Research Office
  • National Institutes of Health
  • National Science Foundation
  • Office of Naval Research
  • Princeton University

Tags

Readers

  • Adaptive Control and Estimation with Uncertainty in Dynamic Systems.
  • Artificial Intelligence
  • Graph Algorithms and Convex Optimization.

Technology Areas

  • AI & ML
  • AI & ML - Bayesian Inference
  • AI & ML - Information Retrieval
  • AI & ML - Machine Learning Algorithms