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), <doi:10.48550/arXiv.2010.07468>; (b) 'adabound' by Luo et al.(2019), <doi:10.48550/arXiv.1902.09843>; (c) 'adahessian' by Yao et al.(2021) <doi:10.48550/arXiv.2006.00719>; (d) 'adamw' by Loshchilov & Hutter (2019), <doi:10.48550/arXiv.1711.05101>; (e) 'madgrad' by Defazio and Jelassi (2021), <doi:10.48550/arXiv.2101.11075>; (f) 'nadam' by Dozat (2019), <https://openreview.net/pdf/OM0jvwB8jIp57ZJjtNEZ.pdf>; (g) 'qhadam' by Ma and Yarats(2019), <doi:10.48550/arXiv.1810.06801>; (h) 'radam' by Liu et al. (2019), <doi:10.48550/arXiv.1908.03265>; (i) 'swats' by Shekar and Sochee (2018), <doi:10.48550/arXiv.1712.07628>; (j) 'yogi' by Zaheer et al.(2019), <https://papers.nips.cc/paper/8186-adaptive-methods-for-nonconvex-optimization>.
| Version: | 0.1.4 |
| Depends: | R (≥ 4.0.0) |
| Imports: | graphics, grDevices, stats, torch |
| Suggests: | testthat |
| Published: | 2023-06-06 |
| DOI: | 10.32614/CRAN.package.torchopt |
| Author: | Gilberto Camara [aut, cre], Rolf Simoes [aut], Daniel Falbel [aut], Felipe Souza [aut] |
| Maintainer: | Gilberto Camara <gilberto.camara.inpe at gmail.com> |
| License: | Apache License (≥ 2) |
| URL: | https://github.com/e-sensing/torchopt/ |
| NeedsCompilation: | no |
| Language: | en-US |
| Materials: | NEWS |
| CRAN checks: | torchopt results |
| Reference manual: | torchopt.html , torchopt.pdf |
| Package source: | torchopt_0.1.4.tar.gz |
| Windows binaries: | r-devel: torchopt_0.1.4.zip, r-release: torchopt_0.1.4.zip, r-oldrel: torchopt_0.1.4.zip |
| macOS binaries: | r-release (arm64): torchopt_0.1.4.tgz, r-oldrel (arm64): torchopt_0.1.4.tgz, r-release (x86_64): torchopt_0.1.4.tgz, r-oldrel (x86_64): torchopt_0.1.4.tgz |
| Old sources: | torchopt archive |
Please use the canonical form https://CRAN.R-project.org/package=torchopt to link to this page.
Need a high-speed mirror for your open-source project?
Contact our mirror admin team at info@clientvps.com.
This archive is provided as a free public service to the community.
Proudly supported by infrastructure from VPSPulse , RxServers , BuyNumber , UnitVPS , OffshoreName and secure payment technology by ArionPay.