Multi-Kernel Gaussian Processes

Melkumyan, Arman; Ramos, Fabio

doi:10.5591/978-1-57735-516-8/IJCAI11-238

Multi-Kernel Gaussian Processes

Arman Melkumyan, Fabio Ramos

Download BibTeX Cite

Proceedings of the Twenty-Second International Joint Conference on Artificial Intelligence. Pages 1408-1412.

https://doi.org/10.5591/978-1-57735-516-8/IJCAI11-238

Abstract

Multi-task learning remains a difficult yet important problem in machine learning. In Gaussian processes the main challenge is the definition of valid kernels (covariance functions) able to capture the relationships between different tasks. This paper presents a novel methodology to construct valid multi-task covariance functions (Mercer kernels) for Gaussian processes allowing for a combination of kernels with different forms. The method is based on Fourier analysis and is general for arbitrary stationary covariance functions. Analytical solutions for cross covariance terms between popular forms are provided including Mat´ern, squared exponential and sparse covariance functions. Experiments are conducted with both artificial and real datasets demonstrating the benefits of the approach.

Arman Melkumyan, and Fabio Ramos. 2011. Multi-Kernel Gaussian Processes. In Proceedings of the Twenty-Second International Joint Conference on Artificial Intelligence, IJCAI-11. IJCAI, 1408–1412. https://doi.org/10.5591/978-1-57735-516-8/IJCAI11-238

@inproceedings{ijcai2011p238,
  title     = {Multi-Kernel Gaussian Processes},
  author    = {Melkumyan, Arman and Ramos, Fabio},
  booktitle = {Proceedings of the Twenty-Second International Joint Conference on
               Artificial Intelligence, {IJCAI-11}},
  publisher = {AAAI Press/International Joint Conferences on Artificial Intelligence},
  editor    = {Toby Walsh},
  pages     = {1408--1412},
  year      = {2011},
  month     = {7},
  doi       = {10.5591/978-1-57735-516-8/IJCAI11-238},
  url       = {https://doi.org/10.5591/978-1-57735-516-8/IJCAI11-238},
}

TY  - CPAPER
TI  - Multi-Kernel Gaussian Processes
AU  - Melkumyan, Arman
AU  - Ramos, Fabio
T2  - Proceedings of the Twenty-Second International Joint Conference on Artificial Intelligence, IJCAI-11
PB  - AAAI Press/International Joint Conferences on Artificial Intelligence
PY  - 2011
SP  - 1408
EP  - 1412
DO  - 10.5591/978-1-57735-516-8/IJCAI11-238
UR  - https://doi.org/10.5591/978-1-57735-516-8/IJCAI11-238
ER  -