Institutions | About Us | Help | Gaeilge
rian logo


Mark
Go Back
Automatic Differentiation in Machine Learning: a Survey
Baydin, Atilim Gunes; Pearlmutter, Barak A.; Radul, Alexey Andreyevich; Siskind, Jeffrey Mark
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 family of techniques similar to but more general than backpropagation for efficiently and accurately evaluating derivatives of numeric functions expressed as computer programs. AD is a small but established field with applications in areas including computational fluid dynamics, atmospheric sciences, and engineering design optimization. Until very recently, the fields of machine learning and AD have largely been unaware of each other and, in some cases, have independently discovered each other’s results. Despite its relevance, general-purpose AD has been missing from the machine learning toolbox, a situation slowly changing with its ongoing adoption under the names “dynamic computational graphs” and “differentiable programming”. We survey the intersection of AD and machine learning, cover applications where AD has direct relevance, and address the main imple- mentation techniques. By precisely defining the main differentiation techniques and their interrelationships, we aim to bring clarity to the usage of the terms “autodiff”, “automatic differentiation”, and “symbolic differentiation” as these are encountered more and more in machine learning settings.
Keyword(s): Backpropagation; Differentiable Programming
Publication Date:
2018
Type: Journal article
Peer-Reviewed: Yes
Institution: Maynooth University
Citation(s): Baydin, Atilim Gunes and Pearlmutter, Barak A. and Radul, Alexey Andreyevich and Siskind, Jeffrey Mark (2018) Automatic Differentiation in Machine Learning: a Survey. Journal of Marchine Learning Research, 18. pp. 1-43. ISSN 1532-4435
Publisher(s): Microtome Publishing
File Format(s): other
Related Link(s): http://mural.maynoothuniversity.ie/10227/1/BP-Automatic-2018.pdf
First Indexed: 2020-04-02 06:17:14 Last Updated: 2020-04-02 06:17:14