English

POGD: Gradient Descent with New Stochastic Rules

Machine Learning 2022-10-20 v1

Abstract

There introduce Particle Optimized Gradient Descent (POGD), an algorithm based on the gradient descent but integrates the particle swarm optimization (PSO) principle to achieve the iteration. From the experiments, this algorithm has adaptive learning ability. The experiments in this paper mainly focus on the training speed to reach the target value and the ability to prevent the local minimum. The experiments in this paper are achieved by the convolutional neural network (CNN) image classification on the MNIST and cifar-10 datasets.

Keywords

Cite

@article{arxiv.2210.10654,
  title  = {POGD: Gradient Descent with New Stochastic Rules},
  author = {Feihu Han and Sida Xing and Sui Yang Khoo},
  journal= {arXiv preprint arXiv:2210.10654},
  year   = {2022}
}
R2 v1 2026-06-28T04:00:31.847Z