Hyperopt-Sklearn: Automatic Hyperparameter Configuration for Scikit-Learn

Proceedings of the 13th Python in Science Conference, 2014

Brent Komer, James Bergstra, Chris Eliasmith

Abstract

Hyperopt-sklearn is a new software project that provides automatic algorithm configuration of the Scikit-learn machine learning library. Following Auto-Weka, we take the view that the choice of classifier and even the choice of preprocessing module can be taken together to represent a single large hyperparameter optimization problem. We use Hyperopt to define a search space that encompasses many standard components (e.g. SVM, RF, KNN, PCA, TFIDF) and common patterns of composing them together. We demonstrate, using search algorithms in Hyperopt and standard benchmarking data sets (MNIST, 20-Newsgroups, Convex Shapes), that searching this space is practical and effective. In particular, we improve on best-known scores for the model space for both MNIST and Convex Shapes.

Full text links

 PDF

 External link

Supplementary information

 Poster

Conference Proceedings

Booktitle
Proceedings of the 13th Python in Science Conference
Pages
33-39

Cite

Plain text

BibTeX