dc.contributor.author | Hückelheim, Jan | |
dc.contributor.author | Menon, Harshitha | |
dc.contributor.author | Moses, William | |
dc.contributor.author | Christianson, Bruce | |
dc.contributor.author | Hovland, Paul | |
dc.contributor.author | Hascoët, Laurent | |
dc.date.accessioned | 2024-09-03T10:30:03Z | |
dc.date.available | 2024-09-03T10:30:03Z | |
dc.date.issued | 2024-09-02 | |
dc.identifier.citation | Hückelheim , J , Menon , H , Moses , W , Christianson , B , Hovland , P & Hascoët , L 2024 , ' A Taxonomy of Automatic Differentiation Pitfalls ' , WIREs: Data Mining and Knowledge Discovery . https://doi.org/10.1002/widm.1555 | |
dc.identifier.issn | 1942-4787 | |
dc.identifier.other | ORCID: /0000-0002-3777-7476/work/166985913 | |
dc.identifier.other | Jisc: 2233411 | |
dc.identifier.uri | http://hdl.handle.net/2299/28117 | |
dc.description | © 2024 UChicago Argonne, LLC and The Author(s). This is an open access article under the terms of the Creative Commons Attribution License, https://creativecommons.org/licenses/by/4.0/ | |
dc.description.abstract | Automatic differentiation is a popular technique for computing derivatives of computer programs. While automatic differentiation has been successfully used in countless engineering, science, and machine learning applications, it can sometimes nevertheless produce surprising results. In this paper, we categorize problematic usages of automatic differentiation, and illustrate each category with examples such as chaos, time-averages, discretizations, fixed-point loops, lookup tables, linear solvers, and probabilistic programs, in the hope that readers may more easily avoid or detect such pitfalls. We also review debugging techniques and their effectiveness in these situations. This article is categorized under: Technologies > Machine Learning. | en |
dc.format.extent | 12 | |
dc.format.extent | 1935587 | |
dc.language.iso | eng | |
dc.relation.ispartof | WIREs: Data Mining and Knowledge Discovery | |
dc.subject | Autodiff, Automatic Differentiation, Backpropagation | |
dc.subject | backpropagation | |
dc.subject | automatic differentiation | |
dc.subject | autodiff | |
dc.subject | General Computer Science | |
dc.title | A Taxonomy of Automatic Differentiation Pitfalls | en |
dc.contributor.institution | School of Physics, Engineering & Computer Science | |
dc.contributor.institution | Centre for Computer Science and Informatics Research | |
dc.description.status | Peer reviewed | |
dc.identifier.url | http://www.scopus.com/inward/record.url?scp=85202982530&partnerID=8YFLogxK | |
rioxxterms.versionofrecord | 10.1002/widm.1555 | |
rioxxterms.type | Journal Article/Review | |
herts.preservation.rarelyaccessed | true | |