2015
StopWasting My Gradients: Practical SVRG
Reza Babanezhad Harikandeh, Mohamed Osama Ahmed, Alim Virani, Mark Schmidt, Jakub Konečný, Scott Sallinen
NeurIPS 2015poster
We present and analyze several strategies for improving the performance ofstochastic variance-reduced gradient (SVRG) methods. We first show that theconvergence rate of these methods can be preserved under a decreasing sequenceof errors in the control variate, and use this to derive variants of SVRG…