All notable changes to libKriging are documented in this file.
The format is based on Keep a Changelog, and this project aims to follow Semantic Versioning.
This file was introduced during the 1.x cycle. For the detailed notes of each past release, see the corresponding entry on the GitHub releases page.
NestedKriging: divide-and-conquer Gaussian process for large designs —
partition of (X, y) into groups with one Kriging submodel each, unified
hyperparameters, and aggregated predictions (PoE / gPoE / BCM / rBCM and the
optimal nested-kriging NK aggregation), with Python/R/Octave/Matlab/Julia
bindings (#317).VLL(m), with local prediction
and a factorization-free "light" mode (#318).windows-2025-vs2026 runner image: CMake pinned to the
version providing the "Visual Studio 18 2026" generator, and Octave/conda
setup (#320).Kriging now accepts
objective="VLL(m)" and the "quadratic" trend, with noise as the last
argument (aligned with Python/WarpKriging); Julia Kriging/NestedKriging
accept a parameters dict like the other classes (#323).CITATION.cff, NOTICE and this changelog, and README features/license/
citation sections (#321).| Version | Date | Notes | |:--------|:-----|:------| | 1.1.0 | 2026-07-08 | NestedKriging for large designs; Vecchia VLL objective; fork/threads, Windows CI and TSan fixes; docs & licensing review. | | 1.0.0 | 2026-05-13 | First stable 1.0 release. | | 0.9.3 | 2026-01-18 | | | 0.9.2 | 2025-12-17 | | | 0.9.1 | 2025-01-14 | | | 0.9.0 | 2024-09-04 | | | 0.8.3 | 2023-12-10 | | | 0.8.2 | 2023-12-10 | | | 0.8.0 | 2023-05-23 | | | 0.7.4 | 2023-01-13 | | | 0.7.3 | 2023-01-09 | | | 0.7.2 | 2022-12-23 | | | 0.7.1 | 2022-12-23 | | | 0.7.0 | 2022-10-06 | | | 0.6.0 | 2022-05-24 | | | 0.5.1 | 2022-04-07 | | | 0.4.8 | 2021-12-05 | | | 0.4.7 | 2021-09-05 | | | 0.4.5 | 2021-09-02 | | | 0.4.4 | 2021-09-02 | | | 0.4.3 | 2021-08-30 | | | 0.4.2 | 2021-06-01 | | | 0.4.1 | 2021-05-31 | First public pre-releases. |
Any scripts or data that you put into this service are public.
Add the following code to your website.
For more information on customizing the embed code, read Embedding Snippets.