On maximization of the information divergence from an exponential family Export

@misc{citeulike:1461209, abstract = {The information divergence of a probability measure P from an exponential family E over a nite set is dened as inmum of the divergences of P from Q subject to Q in E . For convex exponential families the local maximizers of this function of P are found. General exponential family E of dimension d is enlarged to an exponential family E of the dimension at most 3d + 2 such that the local maximizers are of zero divergence from E .}, author = {Matus, Frantisek and Ay, Nihat}, citeulike-article-id = {1461209}, citeulike-linkout-0 = {http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.61.7067}, keywords = {exponential}, posted-at = {2007-07-17 11:09:30}, priority = {2}, title = {On maximization of the information divergence from an exponential family}, url = {http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.61.7067} }

TY - GEN ID - citeulike:1461209 L3 - citeulike-article-id:1461209 N2 - The information divergence of a probability measure P from an exponential family E over a nite set is dened as inmum of the divergences of P from Q subject to Q in E . For convex exponential families the local maximizers of this function of P are found. General exponential family E of dimension d is enlarged to an exponential family E of the dimension at most 3d + 2 such that the local maximizers are of zero divergence from E . TI - On maximization of the information divergence from an exponential family KW - exponential AU - Matus, Frantisek AU - Ay, Nihat UR - http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.61.7067 ER -