SMAC3: A Versatile Bayesian Optimization Package for Hyperparameter Optimization
By Marius Thomas Lindauer, Katharina Eggensperger, Matthias Feurer, André Biedenkapp, Difan Deng, Carolin Benjamins, René Sass, Frank Hutter. Journal of machine learning research, 2021
526 citations recorded by the source corpus.
Algorithm parameters, in particular hyperparameters of machine learning algorithms, can substantially impact their performance. To support users in determining well-performing hyperparameter configurations for their algorithms, datasets and applications at hand, SMAC3 offers a robust and flexible framework for Bayesian Optimization, which can improve performance within a few evaluations. It offers several facades and pre-sets for typical use cases, such as optimizing hyperparameters, solving low dimensional continuous (artificial) global optimization problems and configuring algorithms to perform well across multiple problem instances. The SMAC3 package is available under a permissive BSD-license at https://github.com/automl/SMAC3.
Subfields: Artificial Intelligence, Computational Theory and Mathematics
View Paper: https://www.semanticscholar.org/paper/c3d07f6838e9c50c0bdd0e5b4b761c6f7244b617
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
- Frank Hutter
- Marius Thomas Lindauer
- Katharina Eggensperger
- Shuhei Watanabe
- Stefan Falkner
- Matthias Feurer
- Anne-Laure Boulesteix
- Bernd Bischl
In Computational Theory and Mathematics
- Shuhei Watanabe
- Frank Hutter
- Marius Thomas Lindauer
- Stefan Falkner
- Katharina Eggensperger
- Matthias Feurer
- Anne-Laure Boulesteix
- Bernd Bischl
Citations in the corpus
- Hyperparameter optimization: Foundations, algorithms, best practices, and open challenges (2021, methodology): “For smaller optimization budgets, SMAC-HB is the best multi-fidelity method.”
- Auto-Sklearn 2.0: Hands-free AutoML via Meta-Learning (2020, methodology): “We extended the Bayesian optimization package SMAC3 (Lindauer et al., 2022) to allow for asynchronous parallel optimization.”
- Tree-structured Parzen estimator: Understanding its algorithm components and their roles for better empirical performance (2023, methodology): “, 2021), • Random search (Bergstra & Bengio, 2012): the most basic baseline method in HPO, • SMAC 6 (Hutter et al., 2011; Lindauer et al., 2022): a random forest-based BO method widely used in practice, and • TurBO 7 (Eriksson et al.”