Saving Gradient and Negative Curvature Computations: Finding Local
Minima More Efficiently

Saving Gradient and Negative Curvature Computations: Finding Local Minima More Efficiently

11 December 2017

Quanquan Gu

ArXiv (abs)PDF HTML

Papers citing "Saving Gradient and Negative Curvature Computations: Finding Local Minima More Efficiently"

6 / 6 papers shown

Title
Stochastic Recursive Variance-Reduced Cubic Regularization MethodsInternational Conference on Artificial Intelligence and Statistics (AISTATS), 2019 Dongruo Zhou Quanquan Gu 268 28 0 31 Jan 2019
Finding Local Minima via Stochastic Nested Variance Reduction Dongruo Zhou Pan Xu Quanquan Gu 186 24 0 22 Jun 2018
Stochastic Nested Variance Reduction for Nonconvex Optimization Dongruo Zhou Pan Xu Quanquan Gu 223 158 0 20 Jun 2018
On the Sublinear Convergence of Randomly Perturbed Alternating Gradient Descent to Second Order Stationary Solutions Songtao Lu Mingyi Hong Zhengdao Wang 138 4 0 28 Feb 2018
Stochastic Variance-Reduced Cubic Regularized Newton Method Dongruo Zhou Pan Xu Quanquan Gu ODL 165 46 0 13 Feb 2018
Third-order Smoothness Helps: Even Faster Stochastic Optimization Algorithms for Finding Local Minima Yaodong Yu Pan Xu Quanquan Gu 142 3 0 18 Dec 2017