Train longer, generalize better: closing the generalization gap in large batch training of neural networks

Elad Hoffer, Itay Hubara, Daniel Soudry

Nov-21-2025, 12:12:02 GMT–Neural Information Processing Systems

We examine the initial high learning rate training phase.

artificial intelligence, batch size, machine learning, (15 more...)

Neural Information Processing Systems

Nov-21-2025, 12:12:02 GMT

Conferences PDF

Country:
- North America > United States
  - California > Los Angeles County > Long Beach (0.04)
- Asia > Middle East
  - Israel > Haifa District > Haifa (0.04)

Genre:
- Research Report > New Finding (0.94)

Technology:
- Information Technology > Artificial Intelligence > Machine Learning
  - Statistical Learning (0.95)
  - Neural Networks > Deep Learning (0.69)

Duplicate Docs Excel Report

Title
Train longer, generalize better: closing the generalization gap in large batch training of neural networks
Train longer, generalize better: closing the generalization gap in large batch training of neural networks

Similar Docs Excel Report more

Title	Similarity	Source
None found