Improved Optimization of Finite Sums with Minibatch Stochastic Variance Reduced Proximal Iterations

06/21/2017

∙

by   Jialei Wang, et al.

∙

0

∙

share

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.