A survey of gradient methods for solving nonlinear optimization

I Branislav, M Haifeng, M Dijana - Electronic research archive, 2020 - aimsciences.org
The paper surveys, classifies and investigates theoretically and numerically main classes of
line search methods for unconstrained optimization. Quasi-Newton (QN) and conjugate …

Two-phase switching optimization strategy in deep neural networks

HH Tan, KH Lim - IEEE transactions on neural networks and …, 2020 - ieeexplore.ieee.org
Optimization in a deep neural network is always challenging due to the vanishing gradient
problem and intensive fine-tuning of network hyperparameters. Inspired by multistage …

On the bang-bang control approach via a component-wise line search strategy for unconstrained optimization

MS Lee, HG Harno, BS Goh, KH Lim - Numerical Algebra, Control …, 2020 - aimsciences.org
A bang-bang iteration method equipped with a component-wise line search strategy is
introduced to solve unconstrained optimization problems. The main idea of this method is to …

Nonlinear Least Squares Problems Using Approximate Greatest Descent Method

CNL Eu, HG Harno, KH Lim - 2022 International Conference on …, 2022 - ieeexplore.ieee.org
Many numerical methods have been developed and modified to solve nonlinear least
squares (NLS) problems as unconstrained optimization problems. One of the challenges …