Consistency and Generalization Bounds for Maximum Entropy Density Estimation
Shaojun Wang, Russell Greiner, Shaomin Wang · Entropy · 2013
We investigate the statistical properties of maximum entropy density estimation, both for the complete data case and the incomplete data case. We show that under certain assumptions, the generalization error can be bounded in terms of the complexity of the underlying feature functions. This allows us to establish the universal consistency of maximum entropy density estimation.