no code implementations • 15 Apr 2024 • Nachuan Xiao, Kuangyu Ding, Xiaoyin Hu, Kim-Chuan Toh
Preliminary numerical experiments on deep learning tasks illustrate that our proposed framework yields efficient variants of Lagrangian-based methods with convergence guarantees for nonconvex nonsmooth constrained optimization problems.
no code implementations • 19 Jul 2023 • Nachuan Xiao, Xiaoyin Hu, Kim-Chuan Toh
In this paper, we investigate the convergence properties of the stochastic gradient descent (SGD) method and its variants, especially in training neural networks built from nonsmooth activation functions.
no code implementations • 6 May 2023 • Nachuan Xiao, Xiaoyin Hu, Xin Liu, Kim-Chuan Toh
In this paper, we present a comprehensive study on the convergence properties of Adam-family methods for nonsmooth optimization, especially in the training of nonsmooth neural networks.