pith. sign in

arxiv: 1706.07001 · v2 · pith:KHKO2GNTnew · submitted 2017-06-21 · 🧮 math.OC · cs.LG· stat.ML

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

classification 🧮 math.OC cs.LGstat.ML
keywords empiricalimprovedmethodsminibatchoptimizationreducedstochasticvariance
0
0 comments X
read the original 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.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.