Search Results for author: Lukasz Wesolowski

Found 1 papers, 1 papers with code

Accurate, Large Minibatch SGD: Training ImageNet in 1 Hour

70 code implementations8 Jun 2017 Priya Goyal, Piotr Dollár, Ross Girshick, Pieter Noordhuis, Lukasz Wesolowski, Aapo Kyrola, Andrew Tulloch, Yangqing Jia, Kaiming He

To achieve this result, we adopt a hyper-parameter-free linear scaling rule for adjusting learning rates as a function of minibatch size and develop a new warmup scheme that overcomes optimization challenges early in training.

Stochastic Optimization

Cannot find the paper you are looking for? You can Submit a new open access paper.