26/04/2020

Stochastic Weight Averaging in Parallel: Large-Batch Training That Generalizes Well

Vipul Gupta, Santiago Akle Serrano, Dennis DeCoste

Keywords: Large batch training, Distributed neural network training, Stochastic Weight Averaging

Abstract Paper Similar Papers

Abstract: We propose Stochastic Weight Averaging in Parallel (SWAP), an algorithm to accelerate DNN training. Our algorithm uses large mini-batches to compute an approximate solution quickly and then refines it by averaging the weights of multiple models computed independently and in parallel. The resulting models generalize equally well as those trained with small mini-batches but are produced in a substantially shorter time. We demonstrate the reduction in training time and the good generalization performance of the resulting models on the computer vision datasets CIFAR10, CIFAR100, and ImageNet.

 0
 0
 0
 0
  Share    
This is an embedded video. Talk and the respective paper are published at ICLR 2020 virtual conference. If you are one of the authors of the paper and want to manage your upload, see the question "My papertalk has been externally embedded..." in the FAQ section.

Comments

Post Comment
no comments yet
code of conduct: tbd Characters remaining: 140

Similar Papers

 0
 0
 0
 0
 5:07 
 0
 0
 0
 0
 14:17 
 0
 0
 0
 0
 4:56 
 0
 0
 0
 0
 3:24 
 0
 0
 0
 0
 5:11 
 0
 1
 0
 0
 3:22 
 0
 0
 0
 0
 3:24 
 0
 0
 0
 0
 5:33 
 0
 0
 0
 0
 3:28 
 0
 0
 0
 0
 2:59 
 0
 0
 0
 0
 6:39 
 0
 0
 0
 0
 13:05 
 0
 0
 0
 0
 3:29 
 0
 0
 0
 0
 14:53 
 0
 0
 0
 0
 3:20 
 0
 0
 0
 0
 10:41 
 0
 0
 0
 0
 14:16 
 0
 0
 0
 0
 3:00 
 0
 0
 0
 0
 11:32 
 0
 0
 0
 0
 13:59 
 0
 0
 0
 0
 3:07 
 0
 0
 0
 0
 9:59 
 0
 0
 0
 0
 3:14 
 0
 0
 0
 0
 5:06 
 0
 0
 0
 0
 14:50 
 0
 0
 0
 0
 4:44 
 0
 0
 0
 1
 19:59 
 0
 0
 0
 0
 14:42 
 0
 0
 0
 0
 5:02 
 0
 0
 0
 0
 4:41 
 0
 0
 0
 0
 11:24 
 0
 0
 0
 0
 5:18 
 0
 0
 0
 0
 3:22 
 0
 0
 0
 0
 16:52 
 0
 0
 0
 0
 13:59 
 0
 0
 0
 0
 3:12 
 0
 0
 0
 0
 5:05 
 0
 0
 0
 0
 14:22 
 1
 0
 0
 0
 8:31 
 0
 0
 0
 0
 3:22