A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf
.
On Noisy Negative Curvature Descent: Competing with Gradient Descent for Faster Non-convex Optimization
[article]
2017
arXiv
pre-print
The Hessian-vector product has been utilized to find a second-order stationary solution with strong complexity guarantee (e.g., almost linear time complexity in the problem's dimensionality). In this paper, we propose to further reduce the number of Hessian-vector products for faster non-convex optimization. Previous algorithms need to approximate the smallest eigen-value with a sufficient precision (e.g., ϵ_2≪ 1) in order to achieve a sufficiently accurate second-order stationary solution
arXiv:1709.08571v2
fatcat:ndzw4nwsibaapkenhcdp7ozktm