131 citations · 192 across the 29 of their papers we have counts for
5 papers · 1 filter
On the asymptotic convergence and acceleration of gradient methods
Yakui Huang, Yu-Hong Dai, Xin-Wei Liu +1
We consider the asymptotic behavior of a family of gradient methods, which include the steepest descent and minimal gradient methods as special instances. It is proved that each me…
Combinatorial separation algorithms for the continuous knapsack polyhedra with divisible capacities
Wei-Kun Chen, Yu-Hong Dai
It is important to design separation algorithms of low computational complexity in mixed integer programming. We study the separation problems of the two continuous knapsack polyhe…
Stabilized Barzilai-Borwein method
Oleg Burdakov, Yu-Hong Dai, Na Huang
The Barzilai-Borwein (BB) method is a popular and efficient tool for solving large-scale unconstrained optimization problems. Its search direction is the same as for the steepest d…
Gradient methods exploiting spectral properties
Yakui Huang, Yu-Hong Dai, Xin-Wei Liu +1
We propose a new stepsize for the gradient method. It is shown that this new stepsize will converge to the reciprocal of the largest eigenvalue of the Hessian, when Dai-Yang's asym…
Training GANs with Centripetal Acceleration
Wei Peng, Yuhong Dai, Hui Zhang +1
Training generative adversarial networks (GANs) often suffers from cyclic behaviors of iterates. Based on a simple intuition that the direction of centripetal acceleration of an ob…