Gibbs末端的一般Oracle不等式及其在排序中的应用General Oracle Inequalities for Gibbs Posterior with Application to Ranking |
|
课程网址: | http://videolectures.net/colt2013_li_ranking/ |
主讲教师: | Cheng Li |
开课单位: | 西北大学 |
开课时间: | 2013-08-09 |
课程语种: | 英语 |
中文简介: | 在本文中,我们总结了Li等人的一些最新成果。 (2012),可用于扩展重要的PAC贝叶斯方法,即Gibbs后验,以研究非加性排序风险。该方法基于假设自由风险界限和非渐近oracle不等式,这导致近似最优收敛速度和最优模型选择以平衡近似误差和随机误差。 |
课程简介: | In this paper, we summarize some recent results in Li et al. (2012), which can be used to extend an important PAC-Bayesian approach, namely the Gibbs posterior, to study the nonadditive ranking risk. The methodology is based on assumption-free risk bounds and nonasymptotic oracle inequalities, which leads to nearly optimal convergence rates and optimal model selection to balance the approximation errors and the stochastic errors. |
关 键 词: | 贝叶斯方法; 排序; 最优模型 |
课程来源: | 视频讲座网 |
最后编审: | 2019-03-10:chenxin |
阅读次数: | 94 |