On the incompatibility of faithfulness and monotone DAG faithfulness

On the incompatibility of faithfulness and monotone DAG faithfulness

Cheng, Greiner, Kelly, Bell and Liu [Artificial Intelligence 137 (2002) 43–90] describe an algorithm for learning Bayesian networks that—in a domain consisting of n variables—identifies the optimal solution using O(n4) calls to a mutual-information oracle. This result relies on (1) the standard assumption that the generative distribution is Markov and faithful to some directed acyclic graph (DA...

Monotone DAG Faithfulness: A Bad Assumption

In a recent paper, Cheng, Greiner, Kelly, Bell and Liu (Artificial Intelligence 137:4390; 2002) describe an algorithm for learning Bayesian networks that—in a domain consisting of n variables—identifies the optimal solution using O(n) calls to a mutual-information oracle. This seemingly incredible result relies on (1) the standard assumption that the generative distribution is Markov and faithf...

The Emergence of Faithfulness

Any theory of language development, whether emergentist or nativist, must address the child's phonological development. Children's pronunciations of words are often quite different from those of adults. The child pronunciations may diverge notably from the target adult phonology, but in ways that make sense from a cross-linguistic perspective on the phonological systems of adult languages. In t...

The Theory of Faithfulness

Faithfulness and Reduplicative Identity

1 Workshop at which this work was first presented (Utrecht, June 22-24, 1994). For comments on this material, we are grateful to them and the other workshop participants, especially Austin have provided valuable feedback; and the comments, questions, and suggestions from the participants in the (eventually joint) UMass and Rutgers Correspondence Theory seminars were particularly important for t...