Skip to content
naulon

Not checkedNot checked for notices yet.

Accelerating neural network training with distributed asynchronous and selective optimization (DASO)

Daniel Coquelin, Charlotte Debus, Markus Götz and 4 more

Journal of Big Data · 2022

doi:10.1186/s40537-021-00556-1 (opens in a new tab)

We email you when a new notice or a question about this paper appears.

Abstract

Abstract With increasing data and model complexities, the time required to train neural networks has become prohibitively large. To address the exponential rise in training time, users are turning to data parallel neural networks (DPNN) and large-scale distributed resources on computer clusters. Current DPNN approaches implement the network parameter updates by synchronizing and averaging gradients across all processes with blocking communication operations after each forward-backward pass. This synchronization is the central algorithmic bottleneck. We introduce the distributed asynchronous and selective optimization (DASO) method, which leverages multi-GPU compute node architectures to accelerate network training while maintaining accuracy. DASO uses a hierarchical and asynchronous communication scheme comprised of node-local and global networks while adjusting the global synchronization rate during the learning process. We show that DASO yields a reduction in training time of up to 34% on classical and state-of-the-art networks, as compared to current optimized data parallel training methods.

Abstract licence: CC BY-NC-ND

References45

  1. 13.

39 more references, whose wording the paper’s licence keeps private.

All 45 references

Reads

Read by people on this page

None yet.

Checked or read by AI through naulon

None yet.

A person counts once a day per paper. We keep no cookie and no address: a reader is a hash that changes every day. Any month under five reads shows no number.

Are you an author?

Is this your paper?

Claim it to add your note and be paid when agents cite it. Free.