Tensor Completion with Nearly Linear Samples Given Weak Side Information

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Yu, Christina Lee, Xi, Xumei
Natura: Preprint
Pubblicazione: 2020
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866908468716240896
author Yu, Christina Lee
Xi, Xumei
author_facet Yu, Christina Lee
Xi, Xumei
contents Tensor completion exhibits an interesting computational-statistical gap in terms of the number of samples needed to perform tensor estimation. While there are only $Θ(tn)$ degrees of freedom in a $t$-order tensor with $n^t$ entries, the best known polynomial time algorithm requires $O(n^{t/2})$ samples in order to guarantee consistent estimation. In this paper, we show that weak side information is sufficient to reduce the sample complexity to $O(n)$. The side information consists of a weight vector for each of the modes which is not orthogonal to any of the latent factors along that mode; this is significantly weaker than assuming noisy knowledge of the subspaces. We provide an algorithm that utilizes this side information to produce a consistent estimator with $O(n^{1+κ})$ samples for any small constant $κ> 0$. We also provide experiments on both synthetic and real-world datasets that validate our theoretical insights.
format Preprint
id arxiv_https___arxiv_org_abs_2007_00736
institution arXiv
publishDate 2020
record_format arxiv
spellingShingle Tensor Completion with Nearly Linear Samples Given Weak Side Information
Yu, Christina Lee
Xi, Xumei
Machine Learning
Numerical Analysis
Tensor completion exhibits an interesting computational-statistical gap in terms of the number of samples needed to perform tensor estimation. While there are only $Θ(tn)$ degrees of freedom in a $t$-order tensor with $n^t$ entries, the best known polynomial time algorithm requires $O(n^{t/2})$ samples in order to guarantee consistent estimation. In this paper, we show that weak side information is sufficient to reduce the sample complexity to $O(n)$. The side information consists of a weight vector for each of the modes which is not orthogonal to any of the latent factors along that mode; this is significantly weaker than assuming noisy knowledge of the subspaces. We provide an algorithm that utilizes this side information to produce a consistent estimator with $O(n^{1+κ})$ samples for any small constant $κ> 0$. We also provide experiments on both synthetic and real-world datasets that validate our theoretical insights.
title Tensor Completion with Nearly Linear Samples Given Weak Side Information
topic Machine Learning
Numerical Analysis
url https://arxiv.org/abs/2007.00736