On the loss landscape of a class of deep neural networks with no bad
local valleys

v1v2 (latest)

On the loss landscape of a class of deep neural networks with no bad local valleys

27 September 2018

Quynh N. Nguyen

Mahesh Chandra Mukkamala

Matthias Hein

ArXiv (abs)PDF HTML

Papers citing "On the loss landscape of a class of deep neural networks with no bad local valleys"

10 / 60 papers shown

Title
Convergence Rates of Variational Inference in Sparse Deep Learning Badr-Eddine Chérief-Abdellatif BDL 180 40 0 09 Aug 2019
Are deep ResNets provably better than linear predictors? Chulhee Yun S. Sra Ali Jadbabaie 207 13 0 09 Jul 2019
Explaining Landscape Connectivity of Low-cost Solutions for Multilayer Nets Rohith Kuditipudi Xiang Wang Holden Lee Yi Zhang Zhiyuan Li Wei Hu Sanjeev Arora Rong Ge FAtt 188 95 0 14 Jun 2019
Machine Learning and System Identification for Estimation in Physical Systems Fredrik Bagge Carlson OOD 92 5 0 05 Jun 2019
Traversing the noise of dynamic mini-batch sub-sampled loss functions: A visual guide D. Kafka D. Wilke 86 0 0 20 Mar 2019
On Connected Sublevel Sets in Deep Learning Quynh N. Nguyen 223 105 0 22 Jan 2019
Elimination of All Bad Local Minima in Deep Learning Kenji Kawaguchi L. Kaelbling 172 45 0 02 Jan 2019
On the Benefit of Width for Neural Networks: Disappearance of Bad Basins Dawei Li Tian Ding Ruoyu Sun 247 41 0 28 Dec 2018
Non-attracting Regions of Local Minima in Deep and Wide Neural Networks Henning Petzka C. Sminchisescu 170 10 0 16 Dec 2018
A Priori Estimates of the Population Risk for Two-layer Neural Networks Weinan E Chao Ma Lei Wu 131 139 0 15 Oct 2018