The package implements the hierarchical distribution on precision matrices with an arbitrary, user-specified sparsity pattern proposed in Mastrantonio, Alaimo Di Loro and Mingione, “A new hierarchical distribution on arbitrary sparse precision matrices” (arXiv:2506.09607, 2025). The distribution is built through a sparse Bartlett-type decomposition, allowing direct sampling and Bayesian posterior inference via MCMC for models with sparse Gaussian graphical structures. The source code is archived on Zenodo.
SparseBartlettPackage: Julia package for Bayesian inference with hierarchical priors on sparse precision matrices / Mastrantonio, G., Mingione, M., Alaimo Di Loro, P.. - (2026). [10.5281/zenodo.24020064]
SparseBartlettPackage: Julia package for Bayesian inference with hierarchical priors on sparse precision matrices
Gianluca Mastrantonio;
2026
Abstract
The package implements the hierarchical distribution on precision matrices with an arbitrary, user-specified sparsity pattern proposed in Mastrantonio, Alaimo Di Loro and Mingione, “A new hierarchical distribution on arbitrary sparse precision matrices” (arXiv:2506.09607, 2025). The distribution is built through a sparse Bartlett-type decomposition, allowing direct sampling and Bayesian posterior inference via MCMC for models with sparse Gaussian graphical structures. The source code is archived on Zenodo.Pubblicazioni consigliate
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
https://hdl.handle.net/11583/3017631
