摘要: We give an interpretation of the Maximum Entropy (MaxEnt) Principle in gametheoretic terms. Based on this interpretation, we make a formal distinction between different ways applying distributions. MaxEnt has frequently been criticized grounds that it leads to highly representation dependent results. Our allows us avoid problem many cases.
参考文章(6)
Nir Friedman, Dan Geiger, Moises Goldszmidt, Bayesian Network Classifiers Machine Learning. ,vol. 29, pp. 131- 163 ,(1997) , 10.1023/A:1007465528199
J. Shore, R. Johnson, Axiomatic derivation of the principle of maximum entropy and the principle of minimum cross-entropy IEEE Transactions on Information Theory. ,vol. 26, pp. 26- 37 ,(1980) , 10.1109/TIT.1980.1056144
D. Haussler, A general minimax result for relative entropy IEEE Transactions on Information Theory. ,vol. 43, pp. 1276- 1280 ,(1997) , 10.1109/18.605594
A. J. Grove, J. Y. Halpern, D. Koller, Random worlds and maximum entropy Journal of Artificial Intelligence Research. ,vol. 2, pp. 33- 88 ,(1994) , 10.1613/JAIR.61
Joseph Y. Halpern, Daphne Roller, Representation dependence in probabilistic inference international joint conference on artificial intelligence. pp. 1853- 1860 ,(1995)
Edwin T. Jaynes, Papers on probability, statistics and statistical physics Synthese Library. ,(1983)