Fetching the paper…
Reading the bibliography…
Neural ordinary differential equations (NODEs) is an invertible neural network architecture promising for its free-form Jacobian and the availability of a tractable Jacobian determinant estimator.
“Normalizing Flows for Probabilistic Modeling and Inference”
George Papamakarios, Eric Nalisnick, Danilo Rezende, Shakir Mohamed and Balaji Lakshminarayanan · 1912
Earlier work this paper cites.
“Deep Learning via Dynamical Systems: An Approximation Perspective”
Qianxiao Li, Ting Lin and Zuowei Shen · 1912
Earlier work this paper cites.
T.. Gronwall · 1919
Earlier work this paper cites.
“The Simplicity of Certain Groups of Homeomorphisms”
D… Epstein · 1970
Earlier work this paper cites.
“Foliations and Groups of Diffeomorphisms”
William Thurston · 1974
Earlier work this paper cites.
“Commutators of diffeomorphisms”
John. Mather · 1974
Earlier work this paper cites.
“Commutators of Diffeomorphisms: II”
John. Mather · 1975
Cited alongside, same era.
“A Global Existence and Uniqueness Theorem for Ordinary Differential Equations”
W. Derrick and L. Janos · 1976
Cited alongside, same era.
“Differential Manifolds”
Serge Lang · 1985
Cited alongside, same era.
“Ordinary Differential Equations” 38
Philip Hartman · 2002
Cited alongside, same era.
“Deep Learning”
Yann LeCun, Yoshua Bengio and Geoffrey Hinton · 2015
Cited alongside, same era.
“Neural Ordinary Differential Equations”
Ricky.. Chen, Yulia Rubanova, Jesse Bettencourt and David Duvenaud · 2018
Cited alongside, same era.
“Coupling-Based Invertible Neural Networks Are Universal Diffeomorphism Approximators”
“FFJORD: Free-Form Continuous Dynamics for Scalable Reversible Generative Models”
Will Grathwohl, Ricky.. Chen, Jesse Bettencourt, Ilya Sutskever and David Duvenaud · 2019
Later among the works it cites.
“Sorting out Lipschitz Function Approximation”
Cem Anil, James Lucas and Roger Grosse · 2019
Later among the works it cites.
“Augmented Neural ODEs”
Emilien Dupont, Arnaud Doucet and Yee Teh · 2019
Later among the works it cites.
“How to Train Your Neural ODE: The World of Jacobian and Kinetic Regularization”
Chris Finlay, Jorn-Henrik Jacobsen, Levon Nurbekyan and Adam Oberman · 2020
Closest in time.
“Approximation Capabilities of Neural ODEs and Invertible Residual Networks”
Han Zhang, Xi Gao, Jacob Unterman and Tomasz Arodz · 2020
Closest in time.
alphaXiv searches the wider corpus for related work and actual follow-ups.
alphaXiv is searching for related work…
Takeshi Teshima, Isao Ishikawa, Koichi Tojo, Kenta Oono, Masahiro Ikeda and Masashi Sugiyama
Cited in the paper.