Type: Package
Package: torchopt
Title: Advanced Optimizers for Torch
Version: 0.1.4
Authors@R: c(
    person("Gilberto", "Camara", , "gilberto.camara.inpe@gmail.com", role = c("aut", "cre")),
    person("Rolf", "Simoes", , "rolf.simoes@inpe.br", role = "aut"),
    person("Daniel", "Falbel", , "daniel.falbel@gmail.com", role = "aut"),
    person("Felipe", "Souza", , "felipe.carvalho@inpe.br", role = "aut")
  )
Maintainer: Gilberto Camara <gilberto.camara.inpe@gmail.com>
Description: Optimizers for 'torch' deep learning library. These
        functions include recent results published in the literature
        and are not part of the optimizers offered in 'torch'.
        Prospective users should test these optimizers with their data,
        since performance depends on the specific problem being solved.
        The packages includes the following optimizers: (a) 'adabelief'
        by Zhuang et al (2020), <arXiv:2010.07468>; (b) 'adabound' by
        Luo et al.(2019), <arXiv:1902.09843>; (c) 'adahessian' by Yao
        et al.(2021) <arXiv:2006.00719>; (d) 'adamw' by Loshchilov &
        Hutter (2019), <arXiv:1711.05101>; (e) 'madgrad' by Defazio and
        Jelassi (2021), <arXiv:2101.11075>; (f) 'nadam' by Dozat
        (2019), <https://openreview.net/pdf/OM0jvwB8jIp57ZJjtNEZ.pdf>;
        (g) 'qhadam' by Ma and Yarats(2019), <arXiv:1810.06801>; (h)
        'radam' by Liu et al. (2019), <arXiv:1908.03265>; (i) 'swats'
        by Shekar and Sochee (2018), <arXiv:1712.07628>; (j) 'yogi' by
        Zaheer et al.(2019),
        <https://papers.nips.cc/paper/8186-adaptive-methods-for-nonconvex-optimization>.
License: Apache License (>= 2)
URL: https://github.com/e-sensing/torchopt/
Depends: R (>= 4.0.0)
Imports: graphics, grDevices, stats, torch
Suggests: testthat
ByteCompile: true
Encoding: UTF-8
Language: en-US
Roxygen: list(markdown = TRUE)
RoxygenNote: 7.2.0
Repository: https://e-sensing.r-universe.dev
Date/Publication: 2023-06-08 19:23:07 UTC
RemoteUrl: https://github.com/e-sensing/torchopt
RemoteRef: HEAD
RemoteSha: 399f27b52ac09105ed4b1b1729ac76db73987d0d
NeedsCompilation: no
Packaged: 2026-07-04 06:19:39 UTC; root
Author: Gilberto Camara [aut, cre],
  Rolf Simoes [aut],
  Daniel Falbel [aut],
  Felipe Souza [aut]