Opened 17 months ago

#2498 new defect

Improve Gaussian process training and inference to support larger datasets

Reported by: gkronber Owned by:
Priority: medium Milestone: HeuristicLab 4.0
Component: Algorithms.DataAnalysis Version: 3.3.12
Keywords: Cc:

Description

The most recent and most relevant seems to be KISS-GP which promises big improvements especially for time-series or tempo-spatial data sets. See Andrew Gordon Wilson and Hannes Nickisch, "Kernel interpolation for scalable structured Gaussian processes (KISS-GP)", International Conference on Machine Learning (ICML), 2015 (http://www.cs.cmu.edu/~andrewgw/)

Change History (0)

Note: See TracTickets for help on using tickets.