How Over-Parameterization Slows Down Gradient Descent in Matrix Sensing: The Curses of Symmetry and Initialization

3 October 2023

Papers citing "How Over-Parameterization Slows Down Gradient Descent in Matrix Sensing: The Curses of Symmetry and Initialization"

2 / 2 papers shown

Title
Toward Global Convergence of Gradient EM for Over-Parameterized Gaussian Mixture Models Weihang Xu Maryam Fazel Simon S. Du 23 0 0 29 Jun 2024
Low-Tubal-Rank Tensor Recovery via Factorized Gradient Descent Zhiyu Liu Zhi-Long Han Yandong Tang Xi-Le Zhao Yao Wang 27 1 0 22 Jan 2024