Gradient Descent Efficiency Index

Fuente: arXiv
Saved in:
Bibliographic Details
Main Author: Dhingra, Aviral
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929558184263680
author Dhingra, Aviral
author_facet Dhingra, Aviral
contents Gradient descent is a widely used iterative algorithm for finding local minima in multivariate functions. However, the final iterations often either overshoot the minima or make minimal progress, making it challenging to determine an optimal stopping point. This study introduces a new efficiency metric, Ek, designed to quantify the effectiveness of each iteration. The proposed metric accounts for both the relative change in error and the stability of the loss function across iterations. This measure is particularly valuable in resource-constrained environments, where costs are closely tied to training time. Experimental validation across multiple datasets and models demonstrates that Ek provides valuable insights into the convergence behavior of gradient descent, complementing traditional performance metrics. The index has the potential to guide more informed decisions in the selection and tuning of optimization algorithms in machine learning applications and be used to compare the "effectiveness" of models relative to each other.
format Preprint
id arxiv_https___arxiv_org_abs_2410_19448
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Gradient Descent Efficiency Index
Dhingra, Aviral
Machine Learning
Artificial Intelligence
Optimization and Control
Gradient descent is a widely used iterative algorithm for finding local minima in multivariate functions. However, the final iterations often either overshoot the minima or make minimal progress, making it challenging to determine an optimal stopping point. This study introduces a new efficiency metric, Ek, designed to quantify the effectiveness of each iteration. The proposed metric accounts for both the relative change in error and the stability of the loss function across iterations. This measure is particularly valuable in resource-constrained environments, where costs are closely tied to training time. Experimental validation across multiple datasets and models demonstrates that Ek provides valuable insights into the convergence behavior of gradient descent, complementing traditional performance metrics. The index has the potential to guide more informed decisions in the selection and tuning of optimization algorithms in machine learning applications and be used to compare the "effectiveness" of models relative to each other.
title Gradient Descent Efficiency Index
topic Machine Learning
Artificial Intelligence
Optimization and Control
url https://arxiv.org/abs/2410.19448