Dear All, Suppose we have an incomplete data set D and a known Bayesian network structure Bs, and use EM to learn the parameter for Bs from D. It is possible that the final parameter has longer KL distance to the answer than other parameters obtained during the EM process.
I would like to seek your helps for the following questions: 1. Is there any related work in the topic? 2. Can we call the situation "parameter overfitting"? why not "underfitting" or other terms? If I want to use minimum description length principle as the criterion to choose the parameter, does the description length of the BN differs when I use different parameters but fix the structure? Thank you very much. ------------------------------------------------ Han-Shen Huang Ph.D. Student, Department of CSIE, National Taiwan University E-mail: [EMAIL PROTECTED]
