Applications of fractional calculus in learned optimization

2024/11/22 by Teodor Alexandru Szente, J. Harrison, Szente, Teodor Alexandru +5
Engineering · #Advanced Control Systems Design #FOS: Computer and information sciences #Machine Learning (cs.LG)

paper · pdf · doi:10.48550/arxiv.2411.14855

openalex publication_date 2024/11/22 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

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.

Related

• Enhancing Fractional Gradient Descent with Learned Optimizers
• Fractional Deep Neural Network via Constrained Optimization
• Fractional order graph neural network
• Neural Variable-Order Fractional Differential Equation Networks
• Fractional-order Backpropagation Neural Networks: Modified Fractional-order Steepest Descent Method for Family of Backpropagation Neural Networks