Adding One Neuron Can Eliminate All Bad Local Minima

22 May 2018

Papers citing "Adding One Neuron Can Eliminate All Bad Local Minima"

10 / 10 papers shown

Title
Analysis of the rate of convergence of an over-parametrized convolutional neural network image classifier learned by gradient descent Michael Kohler A. Krzyżak Benjamin Walter 14 1 0 13 May 2024
NTK-SAP: Improving neural network pruning by aligning training dynamics Yite Wang Dawei Li Ruoyu Sun 28 19 0 06 Apr 2023
When Expressivity Meets Trainability: Fewer than $n$ Neurons Can Work Jiawei Zhang Yushun Zhang Mingyi Hong Ruoyu Sun Z. Luo 19 10 0 21 Oct 2022
Noise Regularizes Over-parameterized Rank One Matrix Recovery, Provably Tianyi Liu Yan Li Enlu Zhou Tuo Zhao 30 1 0 07 Feb 2022
Revisiting Landscape Analysis in Deep Neural Networks: Eliminating Decreasing Paths to Infinity Shiyu Liang Ruoyu Sun R. Srikant 25 19 0 31 Dec 2019
Training CNNs with Selective Allocation of Channels Jongheon Jeong Jinwoo Shin CVBM 31 15 0 11 May 2019
Non-attracting Regions of Local Minima in Deep and Wide Neural Networks Henning Petzka C. Sminchisescu 20 9 0 16 Dec 2018
Learning ReLU Networks on Linearly Separable Data: Algorithm, Optimality, and Generalization G. Wang G. Giannakis Jie Chen MLT 22 131 0 14 Aug 2018
Global optimality conditions for deep neural networks Chulhee Yun S. Sra Ali Jadbabaie 121 117 0 08 Jul 2017
The Loss Surfaces of Multilayer Networks A. Choromańska Mikael Henaff Michaël Mathieu Gerard Ben Arous Yann LeCun ODL 175 1,185 0 30 Nov 2014