通过凸二元性统一发散最小化和统计推断Unifying Divergence Minimization and Statistical Inference via Convex Duality |
|
课程网址: | http://videolectures.net/mlss06tw_smola_udmsi/ |
主讲教师: | Alexander J. Smola |
开课单位: | 亚马逊公司 |
开课时间: | 2007-02-25 |
课程语种: | 英语 |
中文简介: | 我们通过凸二元性统一分歧最小化和统计推断。 在这样做的过程中,我们证明近似最大熵估计的对偶是最大后验估计。 此外,我们的治疗导致许多统计学习问题的稳定性和收敛性。 |
课程简介: | 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. Moreover, our treatment leads to stability and convergence bounds for many statistical learning problems. |
关 键 词: | 凸二元性; 统计推断; 对偶 |
课程来源: | 视频讲座网 |
最后编审: | 2020-01-13:chenxin |
阅读次数: | 53 |