1 citations · 1 across the 4 of their papers we have counts for
4 papers
Comment on "First-order methods almost always avoid strict saddle points"
Jinyang Zheng, Yong Xia
The analysis on the global stability of Riemannian gradient descent method in manifold optimization (i.e., it avoids strict saddle points for almost all initializations) due to Lee…
Alternating direction method of multipliers for convex programming: a lift-and-permute scheme
Shiru Li, Yong Xia, Tao Zhang
A lift-and-permute scheme of alternating direction method of multipliers (ADMM) is proposed for linearly constrained convex programming. It contains not only the newly developed ba…
Simultaneous perturbation stochastic approximation: towards one-measurement per iteration
Shiru Li, Yong Xia, Zi Xu
When measuring the value of a function to be minimized is not only expensive but also with noise, the popular simultaneous perturbation stochastic approximation (SPSA) algorithm re…
A new Barzilai-Borwein steplength from the viewpoint of total least squares
Shiru Li, Yong Xia
Barzilai-Borwein (BB) steplength is a popular choice in gradient descent method. By observing that the two existing BB steplengths correspond to the ordinary and the data least squ…