Search Results for author:
Found 2 papers, 0 papers with code
A Stochastic Variance Reduced Gradient using Barzilai-Borwein Techniques as Second Order Information
In this paper, we consider to improve the stochastic variance reduce gradient (SVRG) method via incorporating the curvature information of the objective function.
Nys-Newton: Nyström-Approximated Curvature for Stochastic Optimization
However, the secant equation becomes insipid in approximating the Newton step owing to its use of the first-order derivatives.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
