research
∙
07/15/2022
Riemannian Natural Gradient Methods
This paper studies large-scale optimization problems on Riemannian manif...
share
research
∙
06/14/2021
NG+ : A Multi-Step Matrix-Product Natural Gradient Method for Deep Learning
In this paper, a novel second-order method called NG+ is proposed. By fo...
research
∙
06/17/2020
Structured Stochastic Quasi-Newton Methods for Large-Scale Optimization Problems
In this paper, we consider large-scale finite-sum nonconvex problems ari...
research
∙
06/10/2020