dgpsi v2.5.0

• Training times for DGP emulators are now approximately 30%-40% faster.
• The computation of (D)GP predictions and Leave-One-Out (LOO) evaluations is now 6-7 times faster.
• The nb_parallel argument has been removed from relevant functions, as multi-threading is now integrated by default.
• A Vecchia approximation, implemented under the SI framework, is now available across all functions to support large-scale emulations.
• Two new functions, get_thread_num() and set_thread_num(), allow users to inspect and adjust the number of threads used for multi-threaded computations.
• A new function, set_vecchia(), enables users to easily add or remove the Vecchia approximation for GP, DGP, or linked (D)GP emulators.
• Documentation now includes lifecycle status badges to highlight deprecated and newly introduced functions and arguments.
• The default value of the nugget parameter in DGP emulators with likelihood layers has been adjusted from 1e-6 to 1e-4.
• A Categorical likelihood option has been added to the dgp() function’s likelihood argument, enabling DGP-based classification.
• An issue related to the LD_LIBRARY environment variable on Linux systems has been resolved via the init_py() function.
• The lgp() function has been enhanced to accept connection information among emulators in the form of a data frame, streamlining linked emulation setup.
• A new function, set_id(), allows users to assign unique IDs to emulators.
• The predict() function has been updated to accommodate predictions from DGP classifiers.
• The plot() function has been updated to generate validation plots for DGP classifiers (i.e., DGP emulators with categorical likelihoods) and linked emulators created by lgp() using the new data frame form for struc.
• The summary() function has been redesigned to provide both summary tables and visualizations of structure and model specifications for (D)GP and linked (D)GP emulators.
• A sample_size argument has been added to the validate() and plot() functions, allowing users to adjust the number of samples used for validation when the validation method is set to sampling.
• combine() and set_linked_idx() are deprecated as of this version and will be removed in the next release. These two functions are no longer maintained. Please refer to the updated package documentation for alternative workflows.
• The basic node functions kernel(), Hetero(), Poisson(), and NegBin(), along with the struc argument in the gp() and dgp() functions, have been removed as of this version. Customization of (D)GP specifications can be achieved by modifying the other arguments in gp() and dgp().
• The draw() function has been updated for instances of the bundle class to allow drawing of design and evaluation plots of all emulators in a single figure.
• The plot() function has been updated for linked emulators generated by lgp() using the new data frame form for struc.
• The design() function has been redesigned to allow new specifications of the user-supplied method function.
• The batch_size argument has been added to design() to enable locating multiple design points in a single iteration of the sequential design. This argument is compatible with all built-in method functions: alm(), mice(), and vigf().
• The alm() and vigf() functions have been redesigned to support continuous search for the next design point or search from a discrete candidate set passed through the x_cand argument.
• The alm(), mice(), and vigf() functions have been updated to output the locations of identified design points when a discrete candidate set is not supplied.
• The pei() function has been removed from the package for re-engineering and will be added back in a future version.
• The default of the refit argument in the update() function has been changed from FALSE to TRUE.
• The write() function now allows light = TRUE for both GP emulators and bundles of GP emulators.
• Two new functions, serialize() and deserialize(), have been added to allow users to export emulators to multi-session workers for parallel processing.
• Additional vignettes are available, showcasing large-scale DGP emulation, DGP classification, and Bayesian optimization using (D)GP emulators.
• Enhanced clarity and consistency across the documentation.
• Improved examples and explanations in vignettes for better user guidance.