A Bilevel Optimizer Library in Python for Meta Learning
Reason this release was yanked:
beta version with wrong settings
Project description
Configuration & Status
BOML is a modularized optimization library that unifies several ML algorithms into a common bilevel optimization framework. It provides interfaces to implement popular bilevel optimization algorithms, so that you could quickly build your own meta learning neural network and test its performance.
Key features of BOML
Unified bilevel optimization framework to address different categories of existing meta-learning paradigms.
Modularized algorithmic structure to integrate a variety of optimization techniques and popular methods.
Unit tests with Travis CI and Codecov to reach 99% coverage, and following PEP8 naming convention to guarantee the code quality.
Comprehensive documentations using sphinx and flexible functional interfaces similar to conventional optimizers to help researchers quickly get familiar with the procedures.
Optimization Routine
The figure below illustrates the general optimization routine by organized modules in BOML.
Related Links
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
File details
Details for the file boml-0.1.0.tar.gz.
File metadata
- Download URL: boml-0.1.0.tar.gz
- Upload date:
- Size: 61.9 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/3.2.0 pkginfo/1.5.0.1 requests/2.24.0 setuptools/46.0.0.post20200309 requests-toolbelt/0.9.1 tqdm/4.48.2 CPython/3.7.6
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
39bfe77d05e8e8957a7c9cb7446c06a20af2edc5c19e95c086e18b890db1e7ee
|
|
| MD5 |
ad696acd9c39fc4afda8daee103235f6
|
|
| BLAKE2b-256 |
1ca0d66f5e4b9e9644e58c5a5beefbac283e9c20704239076d6332ecb2e0e368
|
File details
Details for the file boml-0.1.0-py3-none-any.whl.
File metadata
- Download URL: boml-0.1.0-py3-none-any.whl
- Upload date:
- Size: 86.1 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/3.2.0 pkginfo/1.5.0.1 requests/2.24.0 setuptools/46.0.0.post20200309 requests-toolbelt/0.9.1 tqdm/4.48.2 CPython/3.7.6
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
cbfc876428dd6c07f366e1a9bb137034d13441929b555b1babdd78a8c90163c4
|
|
| MD5 |
f054cc0c62cb34003ac5c92a58282fbc
|
|
| BLAKE2b-256 |
33f2191aac951677bcb9f078db553514c243a8cba4b44d046c9e2eeafe010da6
|
