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

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

Kenji Kawaguchi
Jiaoyang Huang
    ODL
ArXivPDFHTML

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

3 / 3 papers shown
Title
Quadratic Suffices for Over-parametrization via Matrix Chernoff Bound
Quadratic Suffices for Over-parametrization via Matrix Chernoff Bound
Zhao Song
Xin Yang
31
91
0
09 Jun 2019
Stochastic Gradient Descent Optimizes Over-parameterized Deep ReLU Networks
Stochastic Gradient Descent Optimizes Over-parameterized Deep ReLU Networks
Difan Zou
Yuan Cao
Dongruo Zhou
Quanquan Gu
ODL
114
448
0
21 Nov 2018
Learning Overparameterized Neural Networks via Stochastic Gradient Descent on Structured Data
Learning Overparameterized Neural Networks via Stochastic Gradient Descent on Structured Data
Yuanzhi Li
Yingyu Liang
MLT
112
652
0
03 Aug 2018