image thumbnail

Whiplash Gradient Descent Algorithm

version 2.3 (474 KB) by Subhransu Sekhar Bhattacharjee
First Order Gradient Descent Algorithm for Stiff-systems.

34 Downloads

Updated 28 Sep 2021

From GitHub

View license on GitHub

Whiplash Gradient Descent: A Closed Loop Gradient Descent Algorithm applied to Rosenbrock's function. Please find the paper here: https://arxiv.org/abs/2108.12883.
We introduce a novel adaptive damping technique for an inertial gradient system which finds application as a gradient descent algorithm for unconstrained optimisation. In an example using the non-convex Rosenbrock's function, we show an improvement on existing momentum-based gradient optimisation methods. Also using Lyapunov stability analysis, we demonstrate the performance of the continuous-time version of the algorithm. Using numerical simulations, we consider the performance of its discrete-time counterpart obtained by using the symplectic Euler method of discretisation.
This file contains a live MATLAB example and a Simulink simulation by Mr. Subhransu Sekhar Bhattacharjee, U7143478, ANU, developed under the supervision of Prof. Dr. Ian R. Petersen FAA, College of Engineering and Computer Science, ANU. Please direct any queries regarding the code to Mr. Subhransu Bhattacharjee at u7143478@anu.edu.au. Please use MATLAB version 2021a for running the .mlx file.

Cite As

Subhransu Sekhar Bhattacharjee & Ian R Petersen, A Closed Loop Gradient Descent Algorithm applied to Rosenbrock's function, Proceedings of the ANZCC 2021, IEEE Xplore, https://github.com/SubhransuSekharBhattacharjee-01/Whiplash, GitHub.

MATLAB Release Compatibility
Created with R2021a
Compatible with any release
Platform Compatibility
Windows macOS Linux

Community Treasure Hunt

Find the treasures in MATLAB Central and discover how the community can help you!

Start Hunting!
To view or report issues in this GitHub add-on, visit the GitHub Repository.
To view or report issues in this GitHub add-on, visit the GitHub Repository.