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

Elad Hoffer, Itay Hubara, Daniel Soudry

Technion - Israel Institute of Technology

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

Fingerprint

Dive into the research topics of 'Train longer, generalize better: closing the generalization gap in large batch training of neural networks: Closing the generalization gap in large batch training of neural networks'. Together they form a unique fingerprint.

Engineering & Materials Science