2 citations · 2 across the 9 of their papers we have counts for
Showing 2023Show all
2 papers · 1 filter
math.OC2023★ 2 cited
Adam-family Methods with Decoupled Weight Decay in Deep Learning
Kuangyu Ding, Nachuan Xiao, Kim-Chuan Toh
In this paper, we investigate the convergence properties of a wide class of Adam-family methods for minimizing quadratically regularized nonsmooth nonconvex optimization problems,…
math.OC2023
On proximal augmented Lagrangian based decomposition methods for dual block-angular convex composite programming problems
Kuang-Yu Ding, Xin-Yee Lam, Kim-Chuan Toh
We design inexact proximal augmented Lagrangian based decomposition methods for convex composite programming problems with dual block-angular structures. Our methods are particular…