conftrace_

gradient staleness

4 papers

Explore in graph

Co-occurring keywords

distributed learning (563) stochastic gradient descent (1091) asynchronous training (22) asynchronous learning (26) asynchronous method (4) error-runtime trade-off (1) mini-batch size (7) asynchronous stochastic gradient descent (13) decoupled learning (6) asynchronous update (9)

Papers

Critical Parameters for Scalable Distributed Learning with Large Batches and Asynchronous Updates AISTATS 2021
Accumulated Decoupled Learning with Gradient Staleness Mitigation for Convolutional Neural Networks ICML 2021
Slow and Stale Gradients Can Win the Race: Error-Runtime Trade-offs in Distributed SGD AISTATS 2018
Accelerating Asynchronous Stochastic Gradient Descent for Neural Machine Translation EMNLP 2018