Heavy-ball Algorithms Always Escape Saddle Points

Heavy-ball Algorithms Always Escape Saddle Points

23 July 2019

Tao Sun

Dongsheng Li

Papers citing "Heavy-ball Algorithms Always Escape Saddle Points"

5 / 5 papers shown

Title
Langevin Multiplicative Weights Update with Applications in Polynomial Portfolio Management Yi-Hu Feng Tianlin Li Tian Xie 67 0 0 26 Feb 2025
Leveraging Continuous Time to Understand Momentum When Training Diagonal Linear Networks Hristo Papazov Scott Pesme Nicolas Flammarion 38 5 0 08 Mar 2024
$Restarted Nonconvex Accelerated Gradient Descent: No More Polylogarithmic Factor in the $O(ε^{-7/4})$ Complexity$ Restarted Nonconvex Accelerated Gradient Descent: No More Polylogarithmic Factor in the $O(ε^{-7/4})$ Complexity Huan Li Zhouchen Lin 44 21 0 27 Jan 2022
Training Deep Neural Networks with Adaptive Momentum Inspired by the Quadratic Optimization Tao Sun Huaming Ling Zuoqiang Shi Dongsheng Li Bao Wang ODL 27 13 0 18 Oct 2021
Stochastic Gradient Langevin Dynamics with Variance Reduction Zhishen Huang Stephen Becker 20 7 0 12 Feb 2021