256 citations · 1k across the 26 of their papers we have counts for
Showing 2015 · cs.LGShow all
2 papers · 2 filters
cs.LG2015★ 1 cited
Efficient Distributed SGD with Variance Reduction
Soham De, Tom Goldstein
Stochastic Gradient Descent (SGD) has become one of the most popular optimization methods for training machine learning models on massive datasets. However, SGD suffers from two ma…
cs.LG2015★ 6 cited
Variance Reduction for Distributed Stochastic Gradient Descent
Soham De, Gavin Taylor, Tom Goldstein
Variance reduction (VR) methods boost the performance of stochastic gradient descent (SGD) by enabling the use of larger, constant stepsizes and preserving linear convergence rates…