Automatic Differentiation
Automatic Differentiation is a computational method that systematically evaluates the exact derivatives of a function by applying the chain rule to elementary arithmetic operations in a computational graph, distinguishing it from symbolic or numerical differentiation through its decomposition of complex functions into analytically differentiable primitives.
838
Publications
70K
Citations
2.2K
Authors
782
Institutions
Publications per year
2017–2026
407
838
Automatic differentiation in PyTorch
Adam Paszke, Sam Gross, Soumith Chintala et al. · 2017 · 11.1K citations
Pymoo: Multi-Objective Optimization in Python
Julian Blank, Kalyanmoy Deb · IEEE Access · 2020 · 2.1K citations · Full text
1–5 of 838
2.2K
23
h-index
16
h-index
11
h-index
10
h-index
Institut national de recherche en sciences et technologies du numérique, France
9 publications · 896 citations
9
h-index
1–5 of 2.2K
782
Argonne National Laboratory
Lemont, United States
27 h-index
107 publications
7K citations
Stanford University
Stanford, United States
21 h-index
91 publications
10.5K citations
Massachusetts Institute of Technology
Cambridge, United States
17 h-index
40 publications
4.2K citations
RWTH Aachen University
Aachen, Germany
17 h-index
65 publications
2.2K citations

Centre National de la Recherche Scientifique
Paris, France
16 h-index
30 publications
1.4K citations
University of Oxford
Oxford, United Kingdom
14 h-index
31 publications
4.6K citations
Institut national de recherche en sciences et technologies du numérique
Le Chesnay-Rocquencourt, France
14 h-index
29 publications
2.2K citations
Princeton University
Princeton, United States
13 h-index
25 publications
1.6K citations
1–8 of 782
Repository · 88 publications · 5.6K citations
32
h-index
TOMS · 29 publications · 3.3K citations
22
h-index
22 publications · 2.9K citations
18
h-index
16 publications · 1.3K citations
14
h-index
TOG · 15 publications · 742 citations
13
h-index
1–5