[1609.04747] An overview of gradient descent optimization algorithms

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.

An overview of gradient descent optimization algorithms∗ Sebastian Ruder Insight Centre for Data Analytics, NUI Galway Aylien Ltd., Dublin arXiv:1609.04747v2 [cs.LG] 15 Jun 2017 ruder.sebastian@gmail.com…

related reading

• An overview of gradient descent optimization algorithmsruder.io
• Why Momentum Really Worksdistill.pub
• A Visual Explanation of Gradient Descent Methods (Momentum, AdaGrad, RMSProp, Adam) | Towards Data Sciencetowardsdatascience.com
• [2101.12176] On the Origin of Implicit Regularization in Stochastic Gradient Descentarxiv.org
• CS231n Deep Learning for Computer Visioncs231n.github.io
• AdaGrad - Cornell University Computational Optimization Open Textbook - Optimization Wikioptimization.cbe.cornell.edu
• The Little Book of Deep Learningfleuret.org
• Calculus on Computational Graphs: Backpropagation -- colah's blogcolah.github.io
• Understanding the Neural Tangent Kernel – EigenTaleseigentales.com
• Understanding Deep Learning Optimizers: Momentum, AdaGrad, RMSProp & Adam | Towards Data Sciencetowardsdatascience.com
• Stochastic gradient descent - Wikipediaen.m.wikipedia.org
• [2605.01172] A Theory of Generalization in Deep Learningarxiv.org