Approximating Hessian matrices using Bayesian inference: a new approach for quasi-Newton methods in stochastic optimization

Optimization methods & software, vol. 39, pp. 1352–1382

Abstract

a new approach for quasi-Newton methods in stochastic optimization,

Authors 3

1. André Gustavo Carlon corresponding

   King Abdullah University of Science and Technology

   Affiliation as printed

   Computer, Electrical and Mathematical Sciences & Engineering Division (CEMSE), King Abdullah University of Science & Technology (KAUST), Thuwal, Saudi Arabia

2. Luis Espath

   University of Nottingham

   Affiliation as printed

   School of Mathematical Sciences, University of Nottingham, Nottingham, UK

3. Raul F. Tempone Aachen Department of Mathematics

   RWTH Aachen University · King Abdullah University of Science and Technology

   Affiliation as printed

   Alexander von Humboldt Professor in Mathematics for Uncertainty Quantification, RWTH Aachen University, Aachen, Germany

   Computer, Electrical and Mathematical Sciences & Engineering Division (CEMSE), King Abdullah University of Science & Technology (KAUST), Thuwal, Saudi Arabia

   Department of Mathematics, RWTH Aachen University, Aachen, Germany