Fast Variance Reduction Method with Stochastic Batch Size

ICML, pp. 3185-3194, 2018.

Cited by: 4|Bibtex|Views17|Links
EI

Abstract:

In this paper we study a family of variance reduction methods with randomized batch size---at each step, the algorithm first randomly chooses the batch size and then selects a batch of samples to conduct a variance-reduced stochastic update. We give the linear convergence rate for this framework for composite functions, and show that the ...More

Code:

Data:

Your rating :
0

 

Tags
Comments