Improved Optimization of Finite Sums with Minibatch Stochastic Variance Reduced Proximal Iterations
Jialei Wang
Tong Zhang

Abstract
We present novel minibatch stochastic optimization methods for empirical risk minimization problems, the methods efficiently leverage variance reduced first-order and sub-sampled higher-order information to accelerate the convergence speed. For quadratic objectives, we prove improved iteration complexity over state-of-the-art under reasonable assumptions. We also provide empirical evidence of the advantages of our method compared to existing approaches in the literature.
View on arXivComments on this paper