.png){kind=icon}
.png){kind=icon}
Return
Training Neural Networks at Any Scale: An exposition
.png){kind=icon}
PRE
AI
T
K
A
L
V
DOI：10.1109/MSP.2026.3667310.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
This article reviews modern optimization methods for training neural networks (NNs) with an emphasis on efficiency and scale. We present state-of-the-art optimization algorithms under a unified algorithmic template that highlights the importance of adapting to the structures in the problem. We then cover how to make these algorithms agnostic to the scale of the problem. Our exposition is intended as an introduction for both practitioners and researchers who wish to be involved in these exciting new developments.
Keywords:
Training
Learning (artificial intelligence)
Neural networks
Artificial intelligence
Optimization methods
Algorithm design and analysis
Deep learning
Closed box
Size control
Journal
IF:
9.6
Papers:
1.1W
Citations:
1.7W
Organization
Cited Papers