02/02/2021

Stability and Generalization of Decentralized Stochastic Gradient Descent

Tao Sun, Dongsheng Li, Bao Wang

Keywords:

Abstract Paper Similar Papers

Abstract: The stability and generalization of stochastic gradient-based methods provide valuable insights into understanding the algorithmic performance of machine learning models. As the main workhorse for deep learning, the stochastic gradient descent has received a considerable amount of studies. Nevertheless, the community paid little attention to its decentralized variants. In this paper, we provide a novel formulation of the decentralized stochastic gradient descent. Leveraging this formulation together with (non)convex optimization theory, we establish the first stability and generalization guarantees for the decentralized stochastic gradient descent. Our theoretical results are built on top of a few common and mild assumptions and reveal that the decentralization deteriorates the stability of SGD for the first time. We verify our theoretical findings by using a variety of decentralized settings and benchmark machine learning models.

The video of this talk cannot be embedded. You can watch it here:
https://slideslive.com/38947821
(Link will open in new window)
 0
 0
 0
 0
  Share    
This is an embedded video. Talk and the respective paper are published at AAAI 2021 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
 12:14 
 0
 0
 0
 0
 8:07 
 0
 0
 0
 0
 14:41 
 0
 0
 0
 0
 18:23 
 0
 0
 0
 0
 3:22 
 0
 0
 0
 0
 14:18 
 0
 0
 0
 0
 5:09 
 0
 0
 0
 0
 5:17 
 0
 0
 0
 0
 13:21 
 0
 0
 0
 0
 3:05 
 0
 0
 0
 0
 16:24 
 0
 0
 0
 0
 15:18 
 0
 0
 0
 0
 4:41 
 1
 1
 0
 0
 2:59 
 0
 0
 0
 1
 15:24 
 0
 0
 0
 0
 3:19 
 0
 0
 0
 0
 20:19 
 0
 0
 0
 0
 14:04 
 0
 0
 0
 0
 14:38 
 0
 0
 0
 0
 3:20 
 0
 0
 0
 0
 4:20 
 0
 0
 0
 0
 16:53 
 0
 0
 0
 0
 17:50 
 0
 0
 0
 0
 3:23 
 0
 0
 0
 0
 5:15 
 0
 0
 0
 0
 15:18 
 0
 0
 0
 0
 5:03 
 0
 0
 0
 0
 14:26 
 0
 0
 0
 0
 3:16 
 0
 0
 0
 0
 10:33 
 0
 0
 0
 0
 5:25 
 1
 1
 0
 0
 14:46 
 0
 0
 0
 0
 4:14 
 0
 0
 0
 0
 3:11 
 0
 0
 0
 0
 14:48 
 0
 0
 0
 0
 14:50 
 0
 0
 0
 0
 8:58 
 0
 0
 0
 0
 13:15 
 0
 0
 0
 0
 4:15 
 0
 0
 0
 0
 4:58