Stochastic gradient descent for linear least squares problems with partially observed data

arXiv2007.04617MaRDI QIDQ6344737FDOQ6344737

Authors: Kui Du, Xiaohui Sun 

Publication date: 9 July 2020

Abstract: We propose a novel stochastic gradient descent method for solving linear least squares problems with partially observed data. Our method uses submatrices indexed by a randomly selected pair of row and column index sets to update the iterate at each step. Theoretical convergence guarantees in the mean square sense are provided. Numerical experiments are reported to demonstrate the theoretical findings.

This page was built for publication: Stochastic gradient descent for linear least squares problems with partially observed data

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6344737)