Parallel Stochastic Newton Method

Abstract

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.

References in corpus (2)

• Randomized Dual Coordinate Ascent with Arbitrary Sampling
• SDNA: Stochastic Dual Newton Ascent for Empirical Risk Minimization

Cited by in corpus (1)

• Newton-Type Methods for Non-Convex Optimization Under Inexact Hessian Information