4 citations · 5 across the 3 of their papers we have counts for
3 papers
math.OC2022
Zeroth-Order Randomized Subspace Newton Methods
Erik Berglund, Sarit Khirirat, Xiaoyu Wang
Zeroth-order methods have become important tools for solving problems where we have access only to function evaluations. However, the zeroth-order methods only using gradient appro…
cs.LG2021★ 1 cited
Bandwidth-based Step-Sizes for Non-Convex Stochastic Optimization
Xiaoyu Wang, Mikael Johansson
Many popular learning-rate schedules for deep neural networks combine a decaying trend with local perturbations that attempt to escape saddle points and bad local minima. We derive…
math.OC2021★ 4 cited
On the Convergence of Step Decay Step-Size for Stochastic Optimization
Xiaoyu Wang, Sindri Magnússon, Mikael Johansson
The convergence of stochastic gradient descent is highly dependent on the step-size, especially on non-convex problems such as neural network training. Step decay step-size schedul…