Saved in:
Bibliographic Details
Main Authors: Gomez-Leos, Alejandro, López, Oscar
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2408.05431
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910570900357120
author Gomez-Leos, Alejandro
López, Oscar
author_facet Gomez-Leos, Alejandro
López, Oscar
contents We revisit the sample and computational complexity of completing a rank-1 tensor in $\otimes_{i=1}^{N} \mathbb{R}^{d}$, given a uniformly sampled subset of its entries. We present a characterization of the problem (i.e. nonzero entries) which admits an algorithm amounting to Gauss-Jordan on a pair of random linear systems. For example, when $N = Θ(1)$, we prove it uses no more than $m = O(d^2 \log d)$ samples and runs in $O(md^2)$ time. Moreover, we show any algorithm requires $Ω(d\log d)$ samples. By contrast, existing upper bounds on the sample complexity are at least as large as $d^{1.5} μ^{Ω(1)} \log^{Ω(1)} d$, where $μ$ can be $Θ(d)$ in the worst case. Prior work obtained these looser guarantees in higher rank versions of our problem, and tend to involve more complicated algorithms.
format Preprint
id arxiv_https___arxiv_org_abs_2408_05431
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Simple and Nearly-Optimal Sampling for Rank-1 Tensor Completion via Gauss-Jordan
Gomez-Leos, Alejandro
López, Oscar
Data Structures and Algorithms
Machine Learning
Statistics Theory
We revisit the sample and computational complexity of completing a rank-1 tensor in $\otimes_{i=1}^{N} \mathbb{R}^{d}$, given a uniformly sampled subset of its entries. We present a characterization of the problem (i.e. nonzero entries) which admits an algorithm amounting to Gauss-Jordan on a pair of random linear systems. For example, when $N = Θ(1)$, we prove it uses no more than $m = O(d^2 \log d)$ samples and runs in $O(md^2)$ time. Moreover, we show any algorithm requires $Ω(d\log d)$ samples. By contrast, existing upper bounds on the sample complexity are at least as large as $d^{1.5} μ^{Ω(1)} \log^{Ω(1)} d$, where $μ$ can be $Θ(d)$ in the worst case. Prior work obtained these looser guarantees in higher rank versions of our problem, and tend to involve more complicated algorithms.
title Simple and Nearly-Optimal Sampling for Rank-1 Tensor Completion via Gauss-Jordan
topic Data Structures and Algorithms
Machine Learning
Statistics Theory
url https://arxiv.org/abs/2408.05431