On the Benefit of Width for Neural Networks: Disappearance of Bad Basins

28 December 2018

Papers citing "On the Benefit of Width for Neural Networks: Disappearance of Bad Basins"

11 / 11 papers shown

Title
Uncovering Critical Sets of Deep Neural Networks via Sample-Independent Critical Lifting Leyang Zhang Tao Luo Yaoyu Zhang BDL 19 0 0 19 May 2025
Architecture independent generalization bounds for overparametrized deep ReLU networks Thomas Chen Chun-Kai Kevin Chien Patrícia Muñoz Ewald Andrew G. Moore 33 0 0 08 Apr 2025
Analyzing the Role of Permutation Invariance in Linear Mode Connectivity Keyao Zhan Puheng Li Lei Wu MoMe 87 0 0 13 Mar 2025
NTK-SAP: Improving neural network pruning by aligning training dynamics Yite Wang Dawei Li Ruoyu Sun 47 19 0 06 Apr 2023
When Expressivity Meets Trainability: Fewer than $n$ Neurons Can Work Jiawei Zhang Yushun Zhang Mingyi Hong Ruoyu Sun Zhi-Quan Luo 34 10 0 21 Oct 2022
A Local Convergence Theory for the Stochastic Gradient Descent Method in Non-Convex Optimization With Non-isolated Local Minima Tae-Eon Ko Xiantao Li 30 2 0 21 Mar 2022
On the Proof of Global Convergence of Gradient Descent for Deep ReLU Networks with Linear Widths Quynh N. Nguyen 56 48 0 24 Jan 2021
Critical Point-Finding Methods Reveal Gradient-Flat Regions of Deep Network Losses Charles G. Frye James B. Simon Neha S. Wadia A. Ligeralde M. DeWeese K. Bouchard ODL 16 2 0 23 Mar 2020
Revisiting Landscape Analysis in Deep Neural Networks: Eliminating Decreasing Paths to Infinity Shiyu Liang Ruoyu Sun R. Srikant 37 19 0 31 Dec 2019
Global optimality conditions for deep neural networks Chulhee Yun S. Sra Ali Jadbabaie 128 118 0 08 Jul 2017
The Loss Surfaces of Multilayer Networks A. Choromańska Mikael Henaff Michaël Mathieu Gerard Ben Arous Yann LeCun ODL 186 1,186 0 30 Nov 2014