vix.ing · top · new · best · stats

An overview of gradient descent optimization algorithms

2016/09/15 by Sebastian Ruder, Ruder, Sebastian · 3 voices · 4,802 citations
Computer Science · Engineering · Mathematics · #Algorithm #Artificial intelligence #Artificial neural network #Computer science #Descent (aeronautics) #Engineering #Face and Expression Recognition #Gradient descent #Mathematical optimization #Mathematics #Medical Image Segmentation Techniques #Optimization algorithm #Stochastic Gradient Optimization Techniques #cs.LG

paper · pdf · doi:10.48550/arxiv.1609.04747

published in arXiv (Cornell University) (Cornell University) · Added derivations of AdaMax and Nadam

openalex publication_date 2016/09/15 · arxiv created 2017/06/15 · arxiv updated 2017/06/16 · openalex created_date 2025/10/10 · openalex updated_date 2026/08/02

Abstract

Gradient descent optimization algorithms, while increasingly popular, are often used as black-box optimizers, as practical explanations of their strengths and weaknesses are hard to come by. This article aims to provide the reader with intuitions with regard to the behaviour of different algorithms that will allow her to put them to use. In the course of this overview, we look at different variants of gradient descent, summarize challenges, introduce the most common optimization algorithms, review architectures in a parallel and distributed setting, and investigate additional strategies for optimizing gradient descent.

Citations

Cited by

Discussions

Related