Gradient Descent Finds Global Minima for Generalizable Deep Neural
Networks of Practical Sizes

v1v2v3 (latest)

Gradient Descent Finds Global Minima for Generalizable Deep Neural Networks of Practical Sizes

5 August 2019

Kenji Kawaguchi

ArXiv (abs)PDF HTML

Papers citing "Gradient Descent Finds Global Minima for Generalizable Deep Neural Networks of Practical Sizes"

7 / 7 papers shown

Title
Quadratic Suffices for Over-parametrization via Matrix Chernoff Bound Zhao Song Xin Yang 66 91 0 09 Jun 2019
Stochastic Gradient Descent Optimizes Over-parameterized Deep ReLU Networks Difan Zou Yuan Cao Dongruo Zhou Quanquan Gu ODL 198 448 0 21 Nov 2018
Depth with Nonlinearity Creates No Bad Local Minima in ResNets Kenji Kawaguchi Yoshua Bengio ODL 91 64 0 21 Oct 2018
Gradient Descent Provably Optimizes Over-parameterized Neural Networks S. Du Xiyu Zhai Barnabás Póczós Aarti Singh MLT ODL 233 1,276 0 04 Oct 2018
Learning Overparameterized Neural Networks via Stochastic Gradient Descent on Structured Data Yuanzhi Li Yingyu Liang MLT 219 653 0 03 Aug 2018
Identity Matters in Deep Learning Moritz Hardt Tengyu Ma OOD 94 399 0 14 Nov 2016
On the Computational Efficiency of Training Neural Networks Roi Livni Shai Shalev-Shwartz Ohad Shamir 146 480 0 05 Oct 2014