We propose a parallel stochastic Newton method (PSN) for minimizing unconstrained smooth convex functions. We analyze the method in the strongly convex case, and give conditions under which acceleration can be expected when compared to its serial counterpart. We show how PSN can be applied to the empirical risk minimization problem, and demonstrate the practical efficiency of the method through numerical experiments and models of simple matrix classes.
@article{arxiv.1705.02005,
title = {Parallel Stochastic Newton Method},
author = {Mojmír Mutný and Peter Richtárik},
journal= {arXiv preprint arXiv:1705.02005},
year = {2017}
}