A note on the statistical view of matrix completion

05/10/2016
by   Tianxi Li, et al.
0

A very simple interpretation of matrix completion problem is introduced based on statistical models. Combined with the well-known results from missing data analysis, such interpretation indicates that matrix completion is still a valid and principled estimation procedure even without the missing completely at random (MCAR) assumption, which almost all of the current theoretical studies of matrix completion assume.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
08/14/2015

Information-theoretic Bounds on Matrix Completion under Union of Subspaces Model

In this short note we extend some of the recent results on matrix comple...
research
03/02/2018

Random perturbation and matrix sparsification and completion

We discuss general perturbation inequalities when the perturbation is ra...
research
10/27/2022

From bilinear regression to inductive matrix completion: a quasi-Bayesian analysis

In this paper we study the problem of bilinear regression and we further...
research
09/30/2021

Causal Matrix Completion

Matrix completion is the study of recovering an underlying matrix from a...
research
11/18/2022

Always Valid Risk Monitoring for Online Matrix Completion

Always-valid concentration inequalities are increasingly used as perform...
research
08/11/2014

Matrix Completion under Interval Uncertainty

Matrix completion under interval uncertainty can be cast as matrix compl...
research
10/04/2019

The Sparse Reverse of Principal Component Analysis for Fast Low-Rank Matrix Completion

Matrix completion constantly receives tremendous attention from many res...

Please sign up or login with your details

Forgot password? Click here to reset