On Large-Batch Training for Deep Learning: Generalization Gap and Sharp Minima
From MaRDI portal
Publication:6277554
arXiv1609.04836MaRDI QIDQ6277554
Jorge Nocedal, Dheevatsa Mudigere, Mikhail Smelyanskiy, Nitish Shirish Keskar, Ping Tak Peter Tang
Publication date: 15 September 2016
Has companion code repository: https://github.com/keskarnitish/large-batch-training
This page was built for publication: On Large-Batch Training for Deep Learning: Generalization Gap and Sharp Minima
