Proposes an incremental variance-reduced stochastic gradient method for minimizing smooth nonconvex composite functions that achieves optimal first-order complexity rates.
Suppose we periodically restart the Algorithm 1 after every T epochs, and set the outputs to be ¯ xk , where k = 1, 2,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
math.OC 1years
2019 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
A Stochastic Composite Gradient Method with Incremental Variance Reduction
Proposes an incremental variance-reduced stochastic gradient method for minimizing smooth nonconvex composite functions that achieves optimal first-order complexity rates.