10.5281/zenodo.61670
https://zenodo.org/records/61670
oai:zenodo.org:61670
Robert T. McGibbon
Robert T. McGibbon
Stanford University
Carlos Hernández
Carlos Hernández
Stanford University
Matthew Harrigan
Matthew Harrigan
Stanford University
Steven Kearnes
Steven Kearnes
Stanford University
Mohammad M. Sultan
Mohammad M. Sultan
Stanford University
Stanislaw Jastrzebski
Stanislaw Jastrzebski
Jagiellonian University
Brooke Husic
Brooke Husic
Stanford University
Osprey v1.1.0
Zenodo
2016
2016-09-06
https://github.com/msmbuilder/osprey/tree/1.1.0
10.5281/zenodo.593238
https://zenodo.org/communities/scientific-python
1.1.0
Apache License 2.0
Osprey is a tool for hyperparameter optimization of machine learning algorithms in Python. Hyperparameter optimization can often be an onerous process for researchers, due to time-consuming experimental replicates, non-convex objective functions, and constant tension between exploration of global parameter space and local optimization. We've designed Osprey to provide scientists with a practical, easy-to-use way of finding optimal model parameters. The software works seamlessly with scikit-learn estimators and supports many different search strategies for choosing the next set of parameters with which to evaluate a given model, including gaussian processes, tree-structured Parzen estimators, as well as random and grid search. As hyperparameter optimization is an embarrassingly parallel problem, Osprey can easily scale to hundreds of concurrent processes by executing a simple command-line program multiple times. This makes it easy to exploit large resources available in high-performance computing environments.
Osprey is actively maintained by researchers at Stanford University and other institutions around the world. While originally developed to analyze computational protein dynamics, it is applicable to any scikit-learn-compatible pipeline. The source code for Osprey is hosted on GitHub and has been archived to Zenodo. Full documentation can be found at http://msmbuilder.org/osprey.