Automatic differentiation in machine learning

BaydinAtılım Günes, A PearlmutterBarak, RadulAlexey Andreyevich, SiskindJeffrey Mark

Journal of Machine Learning Research · 2017 · 84 citations · 0 references

Concepts

Abstract

Derivatives, mostly in the form of gradients and Hessians, are ubiquitous in machine learning. Automatic differentiation (AD), also called algorithmic differentiation or simply auto-diff, is a fa...