A coupled ODE system, discretized with a decreasing learning rate, yields accelerated SGD algorithms with proven optimal last-iterate rates and improved constants.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
math.OC 1years
2019 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Nesterov's method with decreasing learning rate leads to accelerated stochastic gradient descent
A coupled ODE system, discretized with a decreasing learning rate, yields accelerated SGD algorithms with proven optimal last-iterate rates and improved constants.