Applications of fractional calculus in learned optimization
Machine Learning
2024-11-25 v1
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.
Cite
@article{arxiv.2411.14855,
title = {Applications of fractional calculus in learned optimization},
author = {Teodor Alexandru Szente and James Harrison and Mihai Zanfir and Cristian Sminchisescu},
journal= {arXiv preprint arXiv:2411.14855},
year = {2024}
}
Comments
NeurIPS Workshop on Optimization for Machine Learning