Can I read Stochastic quasi-Newton with line-search regularization on EtoBox?

Stochastic quasi-Newton with line-search regularization by Wills, Adrian; Schön, Thomas is a scholarly article available to read on EtoBox.

What is Stochastic quasi-Newton with line-search regularization about?

In this paper we present a novel quasi-Newton algorithm for use in stochastic optimisation. Quasi-Newton methods have had an enormous impact on deterministic optimisation problems because they afford rapid convergence and computationally attractive algorithms. In essence, this is achieved by learning the second-order (Hessian) information based on observing first-order gradients. We extend these ideas to the stochastic setting by employing a highly flexible model for the Hessian and infer its value based on observing noisy gradients. In addition, we propose a stochastic counterpart to standard line-search procedures and demonstrate the utility of this combination on maximum likelihood identification for general nonlinear state space models.

Author

Wills, Adrian; Schön, Thomas

Published

2019

Language

EN