ML Anthology

Improving First-Order Optimization Algorithms (Student Abstract)

Ange Tato, Roger Nkambou
AAAI 2020 pp. 13935-13936
doi:10.1609/AAAI.V34I10.7240 /aaai/2020/tato2020aaai-improving/

Abstract

This paper presents a simple and intuitive technique to accelerate the convergence of first-order optimization algorithms. The proposed solution modifies the update rule, based on the variation of the direction of the gradient and the previous step taken during training. Results after tests show that the technique has the potential to significantly improve the performance of existing first-order optimization algorithms.

PDF AAAI Semantic Scholar

Cite

Text

Tato and Nkambou. "Improving First-Order Optimization Algorithms (Student Abstract)." AAAI Conference on Artificial Intelligence, 2020. doi:10.1609/AAAI.V34I10.7240

Markdown

[Tato and Nkambou. "Improving First-Order Optimization Algorithms (Student Abstract)." AAAI Conference on Artificial Intelligence, 2020.](https://mlanthology.org/aaai/2020/tato2020aaai-improving/) doi:10.1609/AAAI.V34I10.7240

BibTeX

@inproceedings{tato2020aaai-improving,
  title     = {{Improving First-Order Optimization Algorithms (Student Abstract)}},
  author    = {Tato, Ange and Nkambou, Roger},
  booktitle = {AAAI Conference on Artificial Intelligence},
  year      = {2020},
  pages     = {13935-13936},
  doi       = {10.1609/AAAI.V34I10.7240},
  url       = {https://mlanthology.org/aaai/2020/tato2020aaai-improving/}
}