2021; Physical and Mathematical Sciences, 55(1 (254): 29–35
Shared with The Gufo

LOSS FUNCTIONS AND DESCENT METHOD

Hovhannes Zohrabyan*

Received: 2025-01-27 · Published: 2021-05-21

© 2021 The Author(s) and the original publisher.

CC BY-NC 4.0 This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
Shared article.
Original title
LOSS FUNCTIONS AND DESCENT METHOD
Author
Hovhannes Zohrabyan
Published
2021-05-21
Licence
Creative Commons Attribution-NonCommercial 4.0 International
Original
https://doi.org/10.46991/PYSU:A/2021.55.1.029

Abstract

In this paper, we showed that it is possible to use gradient descent method to get minimal error values of loss functions close to their Bayesian estimators. We calculated Bayesian estimators mathematically for different loss functions and tested them using gradient descent algorithm. This algorithm, working on Normal and Poisson distributions showed that it is possible to find minimal error values without having Bayesian estimators. Using Python, we tested the theory on loss functions with known Bayesian estimators as well as another loss functions, getting results proving the theory.
1 / ? 100% Open in new tab Download Cite

Loading the full text…

Download Follow Updates