Functions and Analysis

    

Gradient Descent using Fixed Point Theorem

Authors: Sing Kuang Tan

In this paper, I am going to propose a gradient descent algorithm using fixed point theorem. Fixed point theorem comes from topology mathematics. This gradient descent is able to converge at exponential rate, faster than Netwon method which converges at quadratic rate. Besides that, it does not need second order derivatives. The algorithm is simple and can be implemented using a few lines of equations. It can be used for training Relu deep learning network.

Comments: 8 Pages.

Download: PDF

Submission history

[v1] 2023-02-08 17:28:44

Unique-IP document downloads: 966 times

Vixra.org is a pre-print repository rather than a journal. Articles hosted may not yet have been verified by peer-review and should be treated as preliminary. In particular, anything that appears to include financial or legal advice or proposed medical treatments should be treated with due caution. Vixra.org will not be responsible for any consequences of actions that result from any form of use of any documents on this website.

Add your own feedback and questions here:
You are equally welcome to be positive or negative about any paper but please be polite. If you are being critical you must mention at least one specific error, otherwise your comment will be deleted as unhelpful.

comments powered by Disqus