2020
DOI: 10.48550/arxiv.2007.08880
|View full text |Cite
Preprint
|
Sign up to set email alerts
|

A Differential Game Theoretic Neural Optimizer for Training Residual Networks

Abstract: Connections between Deep Neural Networks (DNNs) training and optimal control theory has attracted considerable attention as a principled tool of algorithmic design. Differential Dynamic Programming (DDP) neural optimizer [1] is a recently proposed method along this line. Despite its empirical success, the applicability has been limited to feedforward networks and whether such a trajectory-optimization inspired framework can be extended to modern architectures remains unclear. In this work, we derive a generali… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...

Citation Types

0
0
0

Year Published

2021
2021
2021
2021

Publication Types

Select...
1

Relationship

0
1

Authors

Journals

citations
Cited by 1 publication
references
References 37 publications
(43 reference statements)
0
0
0
Order By: Relevance