MACHINE LEARNING

Automatic differentiation in machine learning: a survey

Resource type
Authors/contributors
Title
Automatic differentiation in machine learning: a survey
Abstract
Derivatives, mostly in the form of gradients and Hessians, are ubiquitous in machine learning. Automatic differentiation (AD), also called algorithmic differentiation or simply "autodiff", 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 implementation 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.
Publication
arXiv:1502.05767 [cs, stat]
Date
2018-02-05
Short Title
Automatic differentiation in machine learning
Accessed
2019-11-22T22:28:45Z
Library Catalog
Extra
ZSCC: 0000318 arXiv: 1502.05767
Notes
Comment: 43 pages, 5 figures
Citation
Baydin, A. G., Pearlmutter, B. A., Radul, A. A., & Siskind, J. M. (2018). Automatic differentiation in machine learning: a survey. ArXiv:1502.05767 [Cs, Stat]. Retrieved from http://arxiv.org/abs/1502.05767
Attachment
Processing time: 0.02 seconds

Graph of references

(from Zotero to Gephi via Zotnet with this script)
Graph of references