Unifying Divergence Minimization and Statistical Inference Via Convex Duality Export

@incollection{citeulike:2839853, abstract = {In this paper we unify divergence minimization and statistical inference by means of convex duality. In the process of doing so, we prove that the dual of approximate maximum entropy estimation is maximum a posteriori estimation as a special case. Moreover, our treatment leads to stability and convergence bounds for many statistical learning problems. Finally, we show how an algorithm by Zhang can be used to solve this class of optimization problems efficiently.}, author = {Altun, Yasemin and Smola, Alex}, citeulike-article-id = {2839853}, citeulike-linkout-0 = {http://dx.doi.org/10.1007/11776420_13}, doi = {10.1007/11776420_13}, journal = {Learning Theory}, keywords = {class\_probability\_estimation, convexity, divergence, duality, exponential\_family}, pages = {139--153}, posted-at = {2008-05-28 07:48:54}, priority = {5}, title = {Unifying Divergence Minimization and Statistical Inference Via Convex Duality}, url = {http://dx.doi.org/10.1007/11776420_13}, year = {2006} }

TY - CHAP ID - citeulike:2839853 L3 - citeulike-article-id:2839853 N2 - In this paper we unify divergence minimization and statistical inference by means of convex duality. In the process of doing so, we prove that the dual of approximate maximum entropy estimation is maximum a posteriori estimation as a special case. Moreover, our treatment leads to stability and convergence bounds for many statistical learning problems. Finally, we show how an algorithm by Zhang can be used to solve this class of optimization problems efficiently. JF - Learning Theory EP - 153 TI - Unifying Divergence Minimization and Statistical Inference Via Convex Duality SP - 139 KW - class_probability_estimation KW - convexity KW - divergence KW - duality KW - exponential_family AU - Altun, Yasemin AU - Smola, Alex PY - 2006/// UR - http://dx.doi.org/10.1007/11776420_13 ER -