torchopt

torchopt-package

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), <a href="https://arxiv.org/abs/2010.07468">arXiv:2010.07468</a>; (b) 'adabound' by Luo et al.(2019), <a href="https://arxiv.org/abs/1902.09843">arXiv:1902.09843</a>; (c) 'adahessian' by Yao et al.(2021) <a href="https://arxiv.org/abs/2006.00719">arXiv:2006.00719</a>; (d) 'adamw' by Loshchilov &amp; Hutter (2019), <a href="https://arxiv.org/abs/1711.05101">arXiv:1711.05101</a>; (e) 'madgrad' by Defazio and Jelassi (2021), <a href="https://arxiv.org/abs/2101.11075">arXiv:2101.11075</a>; (f) 'nadam' by Dozat (2019), <a href="https://openreview.net/pdf/OM0jvwB8jIp57ZJjtNEZ.pdf">https://openreview.net/pdf/OM0jvwB8jIp57ZJjtNEZ.pdf</a>; (g) 'qhadam' by Ma and Yarats(2019), <a href="https://arxiv.org/abs/1810.06801">arXiv:1810.06801</a>; (h) 'radam' by Liu et al. (2019), <a href="https://arxiv.org/abs/1908.03265">arXiv:1908.03265</a>; (i) 'swats' by Shekar and Sochee (2018), <a href="https://arxiv.org/abs/1712.07628">arXiv:1712.07628</a>; (j) 'yogi' by Zaheer et al.(2019), &lt;https:://papers.nips.cc/paper/8186-adaptive-methods-for-nonconvex-optimization&gt;.

internal

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>.

Gilberto Camara

Advanced Optimizers for Torch

Rolf Simoes

Daniel Falbel

Felipe Souza

torchopt-package function

Maintainer: Gilberto Camara <a href="/link/gilberto.camara%40inpe.br?package=torchopt&version=0.1.4" data-mini-rdoc="torchopt::gilberto.camara@inpe.br">gilberto.camara@inpe.br</a>
Authors:<ul>
<li>Rolf Simoes <a href="/link/rolf.simoes%40inpe.br?package=torchopt&version=0.1.4" data-mini-rdoc="torchopt::rolf.simoes@inpe.br">rolf.simoes@inpe.br</a></li>
<li>Daniel Falbel <a href="/link/daniel.falbel%40gmail.com?package=torchopt&version=0.1.4" data-mini-rdoc="torchopt::daniel.falbel@gmail.com">daniel.falbel@gmail.com</a></li>
<li>Felipe Souza <a href="/link/felipe.carvalho%40inpe.br?package=torchopt&version=0.1.4" data-mini-rdoc="torchopt::felipe.carvalho@inpe.br">felipe.carvalho@inpe.br</a></li>
<li>Alber Sanchez <a href="/link/alber.ipia%40inpe.br?package=torchopt&version=0.1.4" data-mini-rdoc="torchopt::alber.ipia@inpe.br">alber.ipia@inpe.br</a></li>
</ul>

Author

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), <a href='https://arxiv.org/abs/2010.07468'>arXiv:2010.07468</a>; (b) 'adabound' by Luo et al.(2019), <a href='https://arxiv.org/abs/1902.09843'>arXiv:1902.09843</a>; (c) 'adahessian' by Yao et al.(2021) <a href='https://arxiv.org/abs/2006.00719'>arXiv:2006.00719</a>; (d) 'adamw' by Loshchilov &amp; Hutter (2019), <a href='https://arxiv.org/abs/1711.05101'>arXiv:1711.05101</a>; (e) 'madgrad' by Defazio and Jelassi (2021), <a href='https://arxiv.org/abs/2101.11075'>arXiv:2101.11075</a>; (f) 'nadam' by Dozat (2019), <a href='https://openreview.net/pdf/OM0jvwB8jIp57ZJjtNEZ.pdf'>https://openreview.net/pdf/OM0jvwB8jIp57ZJjtNEZ.pdf</a>; (g) 'qhadam' by Ma and Yarats(2019), <a href='https://arxiv.org/abs/1810.06801'>arXiv:1810.06801</a>; (h) 'radam' by Liu et al. (2019), <a href='https://arxiv.org/abs/1908.03265'>arXiv:1908.03265</a>; (i) 'swats' by Shekar and Sochee (2018), <a href='https://arxiv.org/abs/1712.07628'>arXiv:1712.07628</a>; (j) 'yogi' by Zaheer et al.(2019), &lt;https:://papers.nips.cc/paper/8186-adaptive-methods-for-nonconvex-optimization&gt;.

torchopt: Advanced Optimizers for Torch — torchopt-package

Maintainer: Gilberto Camara <a href='mailto:gilberto.camara@inpe.br'>gilberto.camara@inpe.br</a>
Authors:<ul>
<li>Rolf Simoes <a href='mailto:rolf.simoes@inpe.br'>rolf.simoes@inpe.br</a></li>
<li>Daniel Falbel <a href='mailto:daniel.falbel@gmail.com'>daniel.falbel@gmail.com</a></li>
<li>Felipe Souza <a href='mailto:felipe.carvalho@inpe.br'>felipe.carvalho@inpe.br</a></li>
<li>Alber Sanchez <a href='mailto:alber.ipia@inpe.br'>alber.ipia@inpe.br</a></li>
</ul>

Last chance! 50% off unlimited learning

torchopt-package: torchopt: Advanced Optimizers for Torch

Description

Arguments

Author

See Also