图 书 馆
潜在结构概率和斜坡损失的概化边界和一致性Generalization Bounds and Consistency for Latent Structural Probit and Ramp Loss |
|
| 课程网址: | http://videolectures.net/nips2011_mcallester_ramploss/ |
| 主讲教师: | David McAllester |
| 开课单位: | 芝加哥丰田技术学院 |
| 开课时间: | 2012-01-25 |
| 课程语种: | 英语 |
| 中文简介: |  |
| 课程简介: | We consider latent structural versions of probit loss and ramp loss. We show that these surrogate loss functions are consistent in the strong sense that for any feature map (finite or infinite dimensional) they yield predictors approaching the infimum task loss achievable by any linear predictor over the given features. We also give finite sample generalization bounds (convergence rates) for these loss functions. These bounds suggest that probit loss converges more rapidly. However, ramp loss is more easily optimized and may ultimately be more practical. |
| 关 键 词: | 概率损失; 斜率损失; 损失函数 |
| 课程来源: | 视频讲座网 |
| 最后编审: | 2019-09-06：lxf |
| 阅读次数: | 71 |