Parallel Stochastic Newton Method
arXiv:1705.02005
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 (7)
- Distributed Coordinate Descent Method for Learning with Big Data
- Convergence rates of sub-sampled Newton methods
- Sub-Sampled Newton Methods I: Globally Convergent Algorithms
- Sub-Sampled Newton Methods II: Local Convergence Rates
- Distributed Block Coordinate Descent for Minimizing Partially Separable Functions
- Randomized Dual Coordinate Ascent with Arbitrary Sampling
- SDNA: Stochastic Dual Newton Ascent for Empirical Risk Minimization