The BKP package provides tools for Bayesian nonparametric modeling of binary/binomial or categorical/multinomial response data using the Beta Kernel Process (BKP) and its extension, the Dirichlet Kernel Process (DKP). These methods estimate latent probability surfaces through localized kernel smoothing under a Bayesian framework.
The package offers functionality for model fitting, posterior predictive inference with uncertainty quantification, simulation of posterior draws, and visualization in both one- and two-dimensional input spaces. It also supports flexible prior specification and hyperparameter tuning.
Core functionality is organized as follows:
fit_BKP, fit_DKPFit a BKP or DKP model to (multi)binomial response data.
predict.BKP, predict.DKPPerform posterior predictive inference at new input locations, including predictive means, variances, and credible intervals. When observations correspond to single trials (binary or categorical responses), predicted class labels are returned automatically.
simulate.BKP, simulate.DKPGenerate simulated responses from the posterior predictive distribution of a fitted model.
plot.BKP, plot.DKPVisualize model predictions and associated uncertainty in one- and two-dimensional input spaces;
for inputs with more than two dimensions, users can select one or two dimensions
to display via the dims argument.
summary.BKP, summary.DKP, print.BKP, print.DKPSummarize or print the details of a fitted BKP or DKP model.
Zhao J, Qing K, Xu J (2025). BKP: An R Package for Beta Kernel Process Modeling. arXiv. https://doi.org/10.48550/arXiv.2508.10447.
Rolland P, Kavis A, Singla A, Cevher V (2019). Efficient learning of smooth probability functions from Bernoulli tests with guarantees. In Proceedings of the 36th International Conference on Machine Learning, ICML 2019, 9-15 June 2019, Long Beach, California, USA, volume 97 of Proceedings of Machine Learning Research, pp. 5459-5467. PMLR.
MacKenzie CA, Trafalis TB, Barker K (2014). A Bayesian Beta Kernel Model for Binary Classification and Online Learning Problems. Statistical Analysis and Data Mining: The ASA Data Science Journal, 7(6), 434-449.
Goetschalckx R, Poupart P, Hoey J (2011). Continuous Correlated Beta Processes. In Proceedings of the Twenty-Second International Joint Conference on Artificial Intelligence - Volume Volume Two, IJCAI’11, p. 1269-1274. AAAI Press.