Gradient Descent and the Power Method: Exploiting their connection to find the leftmost eigen-pair and escape saddle points

2 November 2022

Papers citing "Gradient Descent and the Power Method: Exploiting their connection to find the leftmost eigen-pair and escape saddle points"

5 / 5 papers shown

Title
Trust-Region Algorithms for Training Responses: Machine Learning Methods Using Indefinite Hessian Approximations Jennifer B. Erway J. Griffin Roummel F. Marcia Riadh Omheni 49 24 0 01 Jul 2018
Accelerated Stochastic Power Iteration Christopher De Sa Bryan D. He Ioannis Mitliagkas Christopher Ré Peng Xu 88 91 0 10 Jul 2017
Gradient Descent Can Take Exponential Time to Escape Saddle Points S. Du Chi Jin Jason D. Lee Michael I. Jordan Barnabás Póczós Aarti Singh 75 244 0 29 May 2017
How to Escape Saddle Points Efficiently Chi Jin Rong Ge Praneeth Netrapalli Sham Kakade Michael I. Jordan ODL 237 838 0 02 Mar 2017
Geometric descent method for convex composite minimization Shixiang Chen Shiqian Ma Wei Liu 61 10 0 29 Dec 2016