Applications of fractional calculus in learned optimization
Lists
Only you see this
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},
}| Enhancing Fractional Gradient Descent with Learned Optimizers | arXiv · 2025 |
| NEO: NEuro-Inspired Optimization—A Fractional Time Series Approach | Frontiers in Physiology · 2021 |
| IF: Iterative Fractional Optimization | Esann · 2021 |
| Learning to Optimize Neural Nets | arXiv · 2017 |
| Learning Gradient Descent: Better Generalization and Longer Horizons | ICML · 2017 |
| Fractional Order Distributed Optimization | arXiv · 2024 |