Statements (60)
Predicate | Object |
---|---|
gptkbp:instance_of |
gptkb:software
|
gptkbp:bfsLayer |
3
|
gptkbp:bfsParent |
gptkb:Pyro
|
gptkbp:application |
hyperparameter tuning
model selection experiment management |
gptkbp:community |
open-source community
|
gptkbp:developed_by |
gptkb:Preferred_Networks
|
gptkbp:features |
visualization tools
multi-objective optimization automatic search space definition |
gptkbp:has_documentation |
https://optuna.readthedocs.io
|
gptkbp:has_feature |
support for multi-threading
support for ensemble methods support for meta-learning support for cloud environments support for natural language processing support for command line interface support for logging and monitoring support for reinforcement learning easy integration with existing code support for feature engineering support for model evaluation support for reproducibility user-friendly API dynamic search space lightweight and flexible support for Jupyter notebooks support for asynchronous execution support for custom objective functions support for custom pruners support for custom samplers support for early stopping support for hyperparameter importance analysis support for image classification support for multi-processing support for parallel execution support for tabular data analysis support for time-series forecasting support for various backends support for various pruners support for various samplers visualization of optimization history |
https://www.w3.org/2000/01/rdf-schema#label |
Optuna
|
gptkbp:influenced_by |
Bayesian optimization
grid search random search TPE (Tree-structured Parzen Estimator) |
gptkbp:language |
gptkb:Library
|
gptkbp:latest_version |
3.0.0
|
gptkbp:license |
MIT License
|
gptkbp:platform |
cross-platform
|
gptkbp:release_date |
gptkb:2019
|
gptkbp:repository |
gptkb:archive
|
gptkbp:supports |
distributed optimization
integration with various ML libraries pruning algorithms |
gptkbp:type |
hyperparameter optimization framework
|
gptkbp:uses |
gptkb:software_framework
deep learning |