High-performance framework for uncertainty quantification, optimization and reinforcement learning.
Korali is a high-performance framework for uncertainty quantification of large-scale models. Korali's multi-language interface allows the execution of any type of computational model, either sequential or distributed (MPI), C++ or Python, and even pre-compiled/legacy applications. Korali's execution engine enables scalable sampling on large-scale HPC systems.
Korali provides a simple interface that allows users to easily describe statistical problems and choose the algorithms to solve them, allowing users to apply a wide range of operations on the same problem with minimal re-configuration efforts. Finally, users can easily extend Korali to describe new problems and test new experimental algorithms
Visit: https://www.cse-lab.ethz.ch/korali/ for more information.
- docs/ Contains all documentation for Korali source and website
- examples/ Contains example scripts that solve all of Korali's problem types
- external/ Contains installation scripts for external libraries required by Korali
- features/ Contains example scripts showcasing Korali's advanced features.
- source/ Contains Korali's source code
- tests/ Contains test scripts to verify Korali's correctness
- tools/ Contains Korali's additional tools and scripts
The Korali Project is developed and maintained by
- Sergio Miguel Martin, martiser at ethz.ch
- Daniel Wälchli, wadaniel at ethz.ch
- Georgios Arampatzis, garampat at ethz.ch
- Pascal Weber, webepasc at ethz.ch
PI:
- Petros Koumoutsakos, petros at ethz.ch
Additional contributors: Lucas Amoudrouz, Ivica Kicic, Fabian Wermelinger, Susanne Keller, Mark Martori.