Optimization of Gaussian Process Hyperparameters using Rprop
Manuel Blum, Martin Riedmiller · The European Symposium on Artificial Neural Networks · 2013
Gaussian processes are a powerful tool for non-parametric re- gression. Training can be realized by maximizing the likelihood of the data given the model. We show that Rprop, a fast and accurate gradient-based optimization technique originally designed for neural network learning, can outperform more elaborate unconstrained optimization methods on real world data sets, where it is able to converge more quickly and reliably to the optimal solution.