163 citations · 1.6k across the 92 of their papers we have counts for
Showing 2017 · math.OCShow all
2 papers · 2 filters
math.OC2017★ 6 cited
NEON+: Accelerated Gradient Methods for Extracting Negative Curvature for Non-Convex Optimization
Yi Xu, Rong Jin, Tianbao Yang
Accelerated gradient (AG) methods are breakthroughs in convex optimization, improving the convergence rate of the gradient descent method for optimization with smooth functions. Ho…
math.OC2017★ 15 cited
First-order Stochastic Algorithms for Escaping From Saddle Points in Almost Linear Time
Yi Xu, Rong Jin, Tianbao Yang
Two classes of methods have been proposed for escaping from saddle points with one using the second-order information carried by the Hessian and the other adding the noise into the…