Efficiently avoiding saddle points with zero order methods: No gradients required

29 October 2019

Papers citing "Efficiently avoiding saddle points with zero order methods: No gradients required"

7 / 7 papers shown

Title
Comparisons Are All You Need for Optimizing Smooth Functions Chenyi Zhang Tongyang Li AAML 37 1 0 19 May 2024
Almost Sure Saddle Avoidance of Stochastic Gradient Methods without the Bounded Gradient Assumption Jun Liu Ye Yuan ODL 19 1 0 15 Feb 2023
Zeroth-Order Negative Curvature Finding: Escaping Saddle Points without Gradients Hualin Zhang Huan Xiong Bin Gu 35 7 0 04 Oct 2022
Stochastic Gradient Langevin Dynamics with Variance Reduction Zhishen Huang Stephen Becker 15 7 0 12 Feb 2021
On the Almost Sure Convergence of Stochastic Gradient Descent in Non-Convex Problems P. Mertikopoulos Nadav Hallak Ali Kavis V. Cevher 30 85 0 19 Jun 2020
A Primer on Zeroth-Order Optimization in Signal Processing and Machine Learning Sijia Liu Pin-Yu Chen B. Kailkhura Gaoyuan Zhang A. Hero III P. Varshney 26 224 0 11 Jun 2020
The Loss Surfaces of Multilayer Networks A. Choromańska Mikael Henaff Michaël Mathieu Gerard Ben Arous Yann LeCun ODL 183 1,186 0 30 Nov 2014