Uncertainty Quantification For Low-Rank Matrix Completion With Heterogeneous and Sub-Exponential Noise

Abstract

The problem of low-rank matrix completion with heterogeneous and sub-exponential (as opposed to homogeneous and Gaussian) noise is particularly relevant to a number of applications in modern commerce. Examples include panel sales data and data collected from web-commerce systems such as recommendation engines. An important unresolved question for this problem is characterizing the distribution of estimated matrix entries under common low-rank estimators. Such a characterization is essential to any application that requires quantification of uncertainty in these estimates and has heretofore only been available under the assumption of homogenous Gaussian noise. Here we characterize the distribution of estimated matrix entries when the observation noise is heterogeneous sub-exponential and provide, as an application, explicit formulas for this distribution when observed entries are Poisson or Binary distributed.

References in corpus (9)

• Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles
• Guaranteed Matrix Completion via Non-convex Factorization
• Implicit Regularization in Nonconvex Statistical Estimation: Gradient Descent Converges Linearly for Phase Retrieval, Matrix Completion, and Blind Deconvolution
• Matrix Completion has No Spurious Local Minimum
• Inference and Uncertainty Quantification for Noisy Matrix Completion
• The Global Optimization Geometry of Low-Rank Matrix Optimization
• Uncertainty Quantification for Matrix Compressed Sensing and Quantum Tomography Problems
• Low-rank matrix completion and denoising under Poisson noise
• Deep density networks and uncertainty in recommender systems