GOODE: A Gaussian Off-The-Shelf Ordinary Differential Equation Solver

Authors: David John, Vincent Heuveline, Michael Schober

ICML 2019 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Numerical experiments and comparison to other solvers are presented in Section 5.
Researcher Affiliation Collaboration 1Corporate Research, Robert Bosch GmbH, Renningen, Germany 2Engineering Mathematics and Computing Lab, Interdisciplinary Center for Scientific Computing, Heidelberg University, Germany 3Bosch Center for Artificial Intelligence, Renningen, Germany.
Pseudocode No The paper does not contain any pseudocode or clearly labeled algorithm blocks.
Open Source Code Yes Matlab code is available at https://github.com/boschresearch/GOODE
Open Datasets Yes The testset can be obtained from Mazzia (2014).
Dataset Splits No The paper refers to a 'testset' which is a collection of problems, not a single dataset with defined train/validation/test splits.
Hardware Specification No The paper does not specify the hardware used for running the experiments.
Software Dependencies No The paper states, 'We have implemented our method in Matlab', but does not provide a specific version number for Matlab or any other software dependencies with version numbers.
Experiment Setup Yes If not stated otherwise, we will use the following default setting to obtain the results: squared exponential kernel, equidistant mesh RN including the boundary points, with N = 31, grid search for λ [1.5h, 15h] with M = 40 logarithmic spaced grid points and ε = 0.1 for all the problems.