Enregistré dans:
Détails bibliographiques
Auteurs principaux: Eleh, Chinedu, Mwanza, Masuzyo, Aguegboh, Ekene, van Wyk, Hans-Werner
Format: Preprint
Publié: 2024
Sujets:
Accès en ligne:https://arxiv.org/abs/2405.16255
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866912404422524928
author Eleh, Chinedu
Mwanza, Masuzyo
Aguegboh, Ekene
van Wyk, Hans-Werner
author_facet Eleh, Chinedu
Mwanza, Masuzyo
Aguegboh, Ekene
van Wyk, Hans-Werner
contents The Adam optimization method has achieved remarkable success in addressing contemporary challenges in stochastic optimization. This method falls within the realm of adaptive sub-gradient techniques, yet the underlying geometric principles guiding its performance have remained shrouded in mystery, and have long confounded researchers. In this paper, we introduce GeoAdaLer (Geometric Adaptive Learner), a novel adaptive learning method for stochastic gradient descent optimization, which draws from the geometric properties of the optimization landscape. Beyond emerging as a formidable contender, the proposed method extends the concept of adaptive learning by introducing a geometrically inclined approach that enhances the interpretability and effectiveness in complex optimization scenarios
format Preprint
id arxiv_https___arxiv_org_abs_2405_16255
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle GeoAdaLer: Geometric Insights into Adaptive Stochastic Gradient Descent Algorithms
Eleh, Chinedu
Mwanza, Masuzyo
Aguegboh, Ekene
van Wyk, Hans-Werner
Machine Learning
Optimization and Control
The Adam optimization method has achieved remarkable success in addressing contemporary challenges in stochastic optimization. This method falls within the realm of adaptive sub-gradient techniques, yet the underlying geometric principles guiding its performance have remained shrouded in mystery, and have long confounded researchers. In this paper, we introduce GeoAdaLer (Geometric Adaptive Learner), a novel adaptive learning method for stochastic gradient descent optimization, which draws from the geometric properties of the optimization landscape. Beyond emerging as a formidable contender, the proposed method extends the concept of adaptive learning by introducing a geometrically inclined approach that enhances the interpretability and effectiveness in complex optimization scenarios
title GeoAdaLer: Geometric Insights into Adaptive Stochastic Gradient Descent Algorithms
topic Machine Learning
Optimization and Control
url https://arxiv.org/abs/2405.16255