Stochastic Gradient Descent for Incomplete Tensor Linear Systems

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Ma, Anna, Needell, Deanna, Xue, Alexander
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910262130376704
author Ma, Anna
Needell, Deanna
Xue, Alexander
author_facet Ma, Anna
Needell, Deanna
Xue, Alexander
contents Solving large tensor linear systems poses significant challenges due to the high volume of data stored, and it only becomes more challenging when some of the data is missing. Recently, Ma et al. showed that this problem can be tackled using a stochastic gradient descent-based method, assuming that the missing data follows a uniform missing pattern. We adapt the technique by modifying the update direction, showing that the method is applicable under other missing data models. We prove convergence results and experimentally verify these results on synthetic data.
format Preprint
id arxiv_https___arxiv_org_abs_2510_07630
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Stochastic Gradient Descent for Incomplete Tensor Linear Systems
Ma, Anna
Needell, Deanna
Xue, Alexander
Numerical Analysis
65F10, 15A69, 65K10
Solving large tensor linear systems poses significant challenges due to the high volume of data stored, and it only becomes more challenging when some of the data is missing. Recently, Ma et al. showed that this problem can be tackled using a stochastic gradient descent-based method, assuming that the missing data follows a uniform missing pattern. We adapt the technique by modifying the update direction, showing that the method is applicable under other missing data models. We prove convergence results and experimentally verify these results on synthetic data.
title Stochastic Gradient Descent for Incomplete Tensor Linear Systems
topic Numerical Analysis
65F10, 15A69, 65K10
url https://arxiv.org/abs/2510.07630