KFAC-like Structured Inverse-Free Natural Gradient Descent

Navigation

Verified details

These details have been verified by PyPI
Maintainers
Avatar for f-dangel from gravatar.com f-dangel

Unverified details

These details have not been verified by PyPI
Project links
Meta
  • License: MIT License (MIT)
  • Author: Wu Lin, Runa Eschenhagen, Felix Dangel, Agustinus Kristiadi, Kirill Neklyudov, Alireza Makhzani
  • Tags natural gradient descent, KFAC
  • Requires: Python >=3.9
  • Provides-Extra: doc, fine-tuning, lint, test
Classifiers

Project description

KFAC-like Structured Inverse-Free Natural Gradient Descent

Project details

Verified details

These details have been verified by PyPI
Maintainers
Avatar for f-dangel from gravatar.com f-dangel

Unverified details

These details have not been verified by PyPI
Project links
Meta
  • License: MIT License (MIT)
  • Author: Wu Lin, Runa Eschenhagen, Felix Dangel, Agustinus Kristiadi, Kirill Neklyudov, Alireza Makhzani
  • Tags natural gradient descent, KFAC
  • Requires: Python >=3.9
  • Provides-Extra: doc, fine-tuning, lint, test
Classifiers

Release history Release notifications | RSS feed

This version

0.0.5

0.0.4

0.0.3

0.0.2

0.0.1

Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

singd-0.0.5.tar.gz (72.1 kB view details)

Uploaded Source

Built Distribution

singd-0.0.5-py3-none-any.whl (43.8 kB view details)

Uploaded Python 3

File details

Details for the file singd-0.0.5.tar.gz.

File metadata

  • Download URL: singd-0.0.5.tar.gz
  • Upload date:
  • Size: 72.1 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/5.1.1 CPython/3.12.7

File hashes

Hashes for singd-0.0.5.tar.gz
Algorithm Hash digest
SHA256 1c26c0762cc8882770bdb4751302193987f8d05b9aab422c76ebd3ca708d5c9b
MD5 a33342c1d8e811f03653453304c17491
BLAKE2b-256 6a18084b271db14191acad976aff5e3f32c76496235e40a6c7162b2f3c8b77c3

See more details on using hashes here.

File details

Details for the file singd-0.0.5-py3-none-any.whl.

File metadata

  • Download URL: singd-0.0.5-py3-none-any.whl
  • Upload date:
  • Size: 43.8 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/5.1.1 CPython/3.12.7

File hashes

Hashes for singd-0.0.5-py3-none-any.whl
Algorithm Hash digest
SHA256 3a0af597368eb0314e00b417581a165d1d01ffba7d612c01204fdb77e1786cfb
MD5 71f0573aaca669d15ad4b936daef86a5
BLAKE2b-256 6737f32154d3dc365ae52e13c5718214dc669e76728e89d731388b2e2d3fad0d

See more details on using hashes here.

Supported by

AWS AWS Cloud computing and Security Sponsor Datadog Datadog Monitoring Fastly Fastly CDN Google Google Download Analytics Microsoft Microsoft PSF Sponsor Pingdom Pingdom Monitoring Sentry Sentry Error logging StatusPage StatusPage Status page