Skip to main content

Multi-iteration Stochastic Estimator

Project description

Multi-iteration Stochastic Estimator

The multi-iteration stochastic estimator (MICE) is an estimator of gradients to be used in stochastic optimization. It uses control-variates to build a hierarchy of iterations, adptively sampling to keep the statistical variance below tolerance in an optimal fashion, cost-wise. The tolerance on the statistical error decreases proportionally to the square of the gradient norm, thus, SGD-MICE converges linearly in strongly convex L-smooth functions.

Project details


Download files

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

Source Distribution

mice-0.1.0.tar.gz (196.2 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

mice-0.1.0-py3-none-any.whl (21.5 kB view details)

Uploaded Python 3

File details

Details for the file mice-0.1.0.tar.gz.

File metadata

  • Download URL: mice-0.1.0.tar.gz
  • Upload date:
  • Size: 196.2 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/3.4.2 importlib_metadata/4.8.1 pkginfo/1.7.1 requests/2.22.0 requests-toolbelt/0.9.1 tqdm/4.46.0 CPython/3.8.10

File hashes

Hashes for mice-0.1.0.tar.gz
Algorithm Hash digest
SHA256 8eb684e4bdc77e1a500d666f21104f0beca9d84c9a86b05ce2d4110960d733cd
MD5 75897ec326c0c761e84b481421182121
BLAKE2b-256 1d31eedf68aee498b18a411c1a9402428af28721b564eaff21742250ea865746

See more details on using hashes here.

File details

Details for the file mice-0.1.0-py3-none-any.whl.

File metadata

  • Download URL: mice-0.1.0-py3-none-any.whl
  • Upload date:
  • Size: 21.5 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/3.4.2 importlib_metadata/4.8.1 pkginfo/1.7.1 requests/2.22.0 requests-toolbelt/0.9.1 tqdm/4.46.0 CPython/3.8.10

File hashes

Hashes for mice-0.1.0-py3-none-any.whl
Algorithm Hash digest
SHA256 628a1d04688f37c46167ba440eb91fe9c8fb57b02f803b1d92fba5793341dc6f
MD5 c616ad270dc116d9fa6fac12487ebe93
BLAKE2b-256 69d2bc883e8b9683fc4d2e4640d6cfe1ba75346e7602be9a1c0d081218e442d1

See more details on using hashes here.

Supported by

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