Saved in:
Bibliographic Details
Main Authors: Borgs, Christian, Chayes, Jennifer, Shah, Devavrat, Yu, Christina Lee
Format: Preprint
Published: 2017
Subjects:
Online Access:https://arxiv.org/abs/1712.00710
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909706940841984
author Borgs, Christian
Chayes, Jennifer
Shah, Devavrat
Yu, Christina Lee
author_facet Borgs, Christian
Chayes, Jennifer
Shah, Devavrat
Yu, Christina Lee
contents We consider sparse matrix estimation where the goal is to estimate an $n\times n$ matrix from noisy observations of a small subset of its entries. We analyze the estimation error of the popularly utilized collaborative filtering algorithm for the sparse regime. Specifically, we propose a novel iterative variant of the algorithm, adapted to handle the setting of sparse observations. We establish that as long as the fraction of entries observed at random scale as $\frac{\log^{1+κ}(n)}{n}$ for any fixed $κ> 0$, the estimation error with respect to the $\max$-norm decays to $0$ as $n\to\infty$ assuming the underlying matrix of interest has constant rank $r$. Our result is robust to model mis-specification in that if the underlying matrix is approximately rank $r$, then the estimation error decays to the approximate error with respect to the $\max$-norm. In the process, we establish algorithm's ability to handle arbitrary bounded noise in the observations.
format Preprint
id arxiv_https___arxiv_org_abs_1712_00710
institution arXiv
publishDate 2017
record_format arxiv
spellingShingle Iterative Collaborative Filtering for Sparse Matrix Estimation
Borgs, Christian
Chayes, Jennifer
Shah, Devavrat
Yu, Christina Lee
Statistics Theory
We consider sparse matrix estimation where the goal is to estimate an $n\times n$ matrix from noisy observations of a small subset of its entries. We analyze the estimation error of the popularly utilized collaborative filtering algorithm for the sparse regime. Specifically, we propose a novel iterative variant of the algorithm, adapted to handle the setting of sparse observations. We establish that as long as the fraction of entries observed at random scale as $\frac{\log^{1+κ}(n)}{n}$ for any fixed $κ> 0$, the estimation error with respect to the $\max$-norm decays to $0$ as $n\to\infty$ assuming the underlying matrix of interest has constant rank $r$. Our result is robust to model mis-specification in that if the underlying matrix is approximately rank $r$, then the estimation error decays to the approximate error with respect to the $\max$-norm. In the process, we establish algorithm's ability to handle arbitrary bounded noise in the observations.
title Iterative Collaborative Filtering for Sparse Matrix Estimation
topic Statistics Theory
url https://arxiv.org/abs/1712.00710