Skip to content

Multi-Output Infinite Horizon Gaussian Process

License

Notifications You must be signed in to change notification settings

MLCS-Yonsei/MultiOutputIHGP

 
 

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

36 Commits
 
 
 
 
 
 
 
 
 
 

Repository files navigation

MultiOutputIHGP

Implementation of the Multi-Output Infinite Horizon Gaussian Process (MOIHGP).

The code includes LBFGS++, which is a header-only c++ implementation of L-BFGS-B algorithm.

Compared to the original MOIHGP, the computation speed has improved by applying Orthogonal Instantaneous Linear Mixing Model (OILMM).

Build

cd moihgp
mkdir build && cd build
cmake ..
make
make install

C++ Examples

  • Regression example
cd moihgp/build
./example_regression
  • Online learning example
cd moihgp/build
./example_online_learning

Python3 Example

  • Online learning example
python3 example.py

Dependencies

Citation

J. Lim, J. Park, S. Nah, & J. Choi. (2021, May). Multi-output Infinite Horizon Gaussian Processes. In 2021 IEEE International Conference on Robotics and Automation (ICRA) (pp. 1542-1549). IEEE. (https://ieeexplore.ieee.org/document/9561031)

@inproceedings{lim2021multi,
  title={Multi-output Infinite Horizon Gaussian Processes},
  author={Lim, Jaehyun and Park, Jehyun and Nah, Sungjae and Choi, Jongeun},
  booktitle={2021 IEEE International Conference on Robotics and Automation (ICRA)},
  pages={1542--1549},
  year={2021},
  organization={IEEE}
}

About

Multi-Output Infinite Horizon Gaussian Process

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • C++ 90.8%
  • Python 7.7%
  • Other 1.5%