图 书 馆
凸风险最小化与条件概率估计Convex Risk Minimization and Conditional Probability Estimation |
|
| 课程网址: | http://videolectures.net/colt2015_telgarsky_conditional_probabili... |
| 主讲教师: | Matus Telgarsky |
| 开课单位: | 加州大学 |
| 开课时间: | 2015-09-09 |
| 课程语种: | 英语 |
| 中文简介: |  |
| 课程简介: | This manuscript strengthens the link between convex risk minimization and conditional probability estimation, a connection already notable for establishing consistency results (Friedman et al., 2000; Zhang, 2004b; Bartlett et al., 2006). Specifically, this manuscript first shows that a loss function, linear space of predictors, and probability measure together define a unique optimal conditional probability model, moreover one which may be attained by the usual convex risk minimization. This result is proved in infinite dimensions, and thus gives a concrete convergence target for unregularized methods like boosting which can fail to have minimizers. Second, this convergence result is refined in finitely many dimensions to hold for empirical risk minimization. This uniform convergence result exhibits no dependence on the norms of its predictors, and thus can justify the practical effectiveness of minimally-regularized optimization schemes. |
| 关 键 词: | 凸风险最小化; 条件概率估计; 收敛目标 |
| 课程来源: | 视频讲座网 |
| 数据采集: | 2022-12-05：chenjy |
| 最后编审: | 2023-05-11：chenjy |
| 阅读次数: | 35 |