This paper presents new results on the complexity of graph-theoretical models that represent probabilities (Bayesian networks) and that represent interval and set valued probabilities (credal networks). We define a new class of networks with bounded width, and introduce a new decision problem for Bayesian networks, the maximin a posteriori. We present new links between the Bayesian and credal networks, and present new results both for Bayesian networks (most probable explanation with observations, maximin a posteriori) and for credal networks (bounds on probabilities a posteriori, most probable explanation with and without observations, maximum a posteriori).
|Original language||American English|
|Number of pages||6|
|State||Published - 1 Dec 2005|
|Event||IJCAI International Joint Conference on Artificial Intelligence - |
Duration: 1 Dec 2005 → …
|Conference||IJCAI International Joint Conference on Artificial Intelligence|
|Period||1/12/05 → …|