Skip to main content

A Python toolbox for performing gradient-free optimization

Project description

Support Ukraine CircleCI

Nevergrad - A gradient-free optimization platform

Nevergrad

nevergrad is a Python 3.8+ library. It can be installed with:

pip install nevergrad

More installation options, including windows installation, and complete instructions are available in the "Getting started" section of the documentation.

You can join Nevergrad users Facebook group here.

Minimizing a function using an optimizer (here NGOpt) is straightforward:

import nevergrad as ng

def square(x):
    return sum((x - .5)**2)

optimizer = ng.optimizers.NGOpt(parametrization=2, budget=100)
recommendation = optimizer.minimize(square)
print(recommendation.value)  # recommended value
>>> [0.49971112 0.5002944]

nevergrad can also support bounded continuous variables as well as discrete variables, and mixture of those. To do this, one can specify the input space:

import nevergrad as ng

def fake_training(learning_rate: float, batch_size: int, architecture: str) -> float:
    # optimal for learning_rate=0.2, batch_size=4, architecture="conv"
    return (learning_rate - 0.2)**2 + (batch_size - 4)**2 + (0 if architecture == "conv" else 10)

# Instrumentation class is used for functions with multiple inputs
# (positional and/or keywords)
parametrization = ng.p.Instrumentation(
    # a log-distributed scalar between 0.001 and 1.0
    learning_rate=ng.p.Log(lower=0.001, upper=1.0),
    # an integer from 1 to 12
    batch_size=ng.p.Scalar(lower=1, upper=12).set_integer_casting(),
    # either "conv" or "fc"
    architecture=ng.p.Choice(["conv", "fc"])
)

optimizer = ng.optimizers.NGOpt(parametrization=parametrization, budget=100)
recommendation = optimizer.minimize(fake_training)

# show the recommended keyword arguments of the function
print(recommendation.kwargs)
>>> {'learning_rate': 0.1998, 'batch_size': 4, 'architecture': 'conv'}

Learn more on parametrization in the documentation!

Example of optimization

Convergence of a population of points to the minima with two-points DE.

Documentation

Check out our documentation! It's still a work in progress, so don't hesitate to submit issues and/or pull requests (PRs) to update it and make it clearer! The last version of our data and the last version of our PDF report.

Citing

@misc{nevergrad,
    author = {J. Rapin and O. Teytaud},
    title = {{Nevergrad - A gradient-free optimization platform}},
    year = {2018},
    publisher = {GitHub},
    journal = {GitHub repository},
    howpublished = {\url{https://GitHub.com/FacebookResearch/Nevergrad}},
}

License

nevergrad is released under the MIT license. See LICENSE for additional details about it. See also our Terms of Use and Privacy Policy.

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

nevergrad-1.0.5.tar.gz (403.2 kB view details)

Uploaded Source

Built Distribution

nevergrad-1.0.5-py3-none-any.whl (495.7 kB view details)

Uploaded Python 3

File details

Details for the file nevergrad-1.0.5.tar.gz.

File metadata

  • Download URL: nevergrad-1.0.5.tar.gz
  • Upload date:
  • Size: 403.2 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/5.1.1 CPython/3.9.20

File hashes

Hashes for nevergrad-1.0.5.tar.gz
Algorithm Hash digest
SHA256 c341c767067543ada280669118cfc1d2db7eb2610bedb4b7cc3d6ae7ea98955d
MD5 c9e06f0e723e61c27ac0c3d801803507
BLAKE2b-256 00f35f804311ba9c4e617ad419660c7597690123335daf90a0e5eac71fd1c9b5

See more details on using hashes here.

Provenance

File details

Details for the file nevergrad-1.0.5-py3-none-any.whl.

File metadata

  • Download URL: nevergrad-1.0.5-py3-none-any.whl
  • Upload date:
  • Size: 495.7 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/5.1.1 CPython/3.9.20

File hashes

Hashes for nevergrad-1.0.5-py3-none-any.whl
Algorithm Hash digest
SHA256 bfabc7a45cf172aef551c13892329a2ecd30f18cc5493aef4dc7cb84180140bb
MD5 a7fa4ecc71afc36b8bc158365db98a84
BLAKE2b-256 a94e3d02e74c06ce2eeb6d39b7654e0b527ae4620debf3f85205522c20b9d2ab

See more details on using hashes here.

Provenance

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