R-DACH places a horseshoe prior on the Cholesky factor of a DAG precision matrix plus per-observation scale mixtures, yielding posterior contraction and skeleton consistency in the proportional high-dimensional regime under heavy tails.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
stat.ME 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Bayesian DAG Structure Learning with Simultaneous Shrinkage Covariance Estimation under Scale-Mixture Error Distributions in the Proportional High-Dimensional Regime
R-DACH places a horseshoe prior on the Cholesky factor of a DAG precision matrix plus per-observation scale mixtures, yielding posterior contraction and skeleton consistency in the proportional high-dimensional regime under heavy tails.