rkeops (1.4.1)

0 users

Kernel Operations on the GPU, with Autodiff, without Memory Overflows.


The 'KeOps' library lets you compute generic reductions of very large arrays whose entries are given by a mathematical formula. It combines a tiled reduction scheme with an automatic differentiation engine, and can be used through 'R', 'Matlab', 'NumPy' or 'PyTorch' backends. It is perfectly suited to the computation of Kernel dot products and the associated gradients, even when the full kernel matrix does not fit into the GPU memory.

Maintainer: Ghislain Durif
Author(s): Benjamin Charlier [aut] (<http://imag.umontpellier.fr/~charlier/>), Jean Feydy [aut] (<https://www.math.ens.fr/~feydy/>), Joan A. Glauns [aut] (<https://www.mi.parisdescartes.fr/~glaunes/>), Ghislain Durif [aut, cre] (<https://gdurif.perso.math.cnrs.fr/>), Franois-David Collin [ctb] (Development-related consulting and support), Daniel Frey [ctb] (Author of the included C++ library 'sequences')

License: MIT + file LICENSE

Uses: openssl, Rcpp, stringr, testthat, knitr, rmarkdown

Released 8 days ago.

1 previous version



  (0 votes)


  (0 votes)

Log in to vote.


No one has written a review of rkeops yet. Want to be the first? Write one now.

Related packages:(20 best matches, based on common tags.)

Search for rkeops on google, google scholar, r-help, r-devel.

Visit rkeops on R Graphical Manual.