Arip Rahman - Academia.edu (original) (raw)
Uploads
Papers by Arip Rahman
UAI'95, 1995
We present a simple characterization of equivalent B a yesian network structures based on local t... more We present a simple characterization of equivalent B a yesian network structures based on local transformations. The signi cance of the characterization is twofold. First, we are able to easily prove s e v eral new invariant properties of theoretical interest for equivalent structures. Second, we use the characterization to derive an e cient algorithm that identi es all of the compelled edges in a structure. Compelled edge identication is of particular importance for learning Bayesian network structures from data because these edges indicate causal relationships when certain assumptions hold.
UAI'95, 1995
We present a simple characterization of equivalent B a yesian network structures based on local t... more We present a simple characterization of equivalent B a yesian network structures based on local transformations. The signi cance of the characterization is twofold. First, we are able to easily prove s e v eral new invariant properties of theoretical interest for equivalent structures. Second, we use the characterization to derive an e cient algorithm that identi es all of the compelled edges in a structure. Compelled edge identication is of particular importance for learning Bayesian network structures from data because these edges indicate causal relationships when certain assumptions hold.