Applications of fractional calculus in learned optimization

Teodor Alexandru Szente, James Harrison, Mihai Zanfir, Cristian Sminchisescu

Abstract

Fractional gradient descent has been studied extensively, with a focus on its ability to extend traditional gradient descent methods by incorporating fractional-order derivatives. This approach allows for more flexibility in navigating complex optimization landscapes and offers advantages in certain types of problems, particularly those involving non-linearities and chaotic dynamics. Yet, the challenge of fine-tuning the fractional order parameters remains unsolved. In this work, we demonstrate that it is possible to train a neural network to predict the order of the gradient effectively.
BibTeX
@misc{szente2024applications,
  author = {Teodor Alexandru Szente and James Harrison and Mihai Zanfir and Cristian Sminchisescu},
  title = {{Applications of fractional calculus in learned optimization}},
  year = {2024},
  eprint = {2411.14855},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2411.14855},
}
Figure