Super Gradient Descent: Global Optimization requires Global Gradient

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autore principale: Achour, Seifeddine
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866910677729280000
author Achour, Seifeddine
author_facet Achour, Seifeddine
contents Global minimization is a fundamental challenge in optimization, especially in machine learning, where finding the global minimum of a function directly impacts model performance and convergence. This article introduces a novel optimization method that we called Super Gradient Descent, designed specifically for one-dimensional functions, guaranteeing convergence to the global minimum for any k-Lipschitz function defined on a closed interval [a, b]. Our approach addresses the limitations of traditional optimization algorithms, which often get trapped in local minima. In particular, we introduce the concept of global gradient which offers a robust solution for precise and well-guided global optimization. By focusing on the global minimization problem, this work bridges a critical gap in optimization theory, offering new insights and practical advancements in different optimization problems in particular Machine Learning problems like line search.
format Preprint
id arxiv_https___arxiv_org_abs_2410_19706
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Super Gradient Descent: Global Optimization requires Global Gradient
Achour, Seifeddine
Machine Learning
Numerical Analysis
Optimization and Control
Global minimization is a fundamental challenge in optimization, especially in machine learning, where finding the global minimum of a function directly impacts model performance and convergence. This article introduces a novel optimization method that we called Super Gradient Descent, designed specifically for one-dimensional functions, guaranteeing convergence to the global minimum for any k-Lipschitz function defined on a closed interval [a, b]. Our approach addresses the limitations of traditional optimization algorithms, which often get trapped in local minima. In particular, we introduce the concept of global gradient which offers a robust solution for precise and well-guided global optimization. By focusing on the global minimization problem, this work bridges a critical gap in optimization theory, offering new insights and practical advancements in different optimization problems in particular Machine Learning problems like line search.
title Super Gradient Descent: Global Optimization requires Global Gradient
topic Machine Learning
Numerical Analysis
Optimization and Control
url https://arxiv.org/abs/2410.19706