图 书 馆
用贝斯近似法不能做到的东西What cannot be learned with Bethe Approximations |
|
| 课程网址: | http://videolectures.net/nipsworkshops2012_globerson_bethe_approx... |
| 主讲教师: | Amir Globerson |
| 开课单位: | 耶路撒冷希伯来大学 |
| 开课时间: | 2013-01-16 |
| 课程语种: | 英语 |
| 中文简介: |  |
| 课程简介: | We address the problem of learning the parameters in graphical models when inference is intractable. A common strategy in this case is to replace the partition function with its Bethe approximation. However not much is known about the theoretical properties of such approximations. Here we show that there exists a regime of empirical marginals where such "Bethe learning" will fail. By failure we mean that moment matching will not be achieved. We provide several conditions on empirical marginals that yield outer and inner bounds on the set of Bethe learnable marginals. An interesting implication of our results is that there exists a large class of marginals that cannot be obtained as stable fixed points of belief propagation. Taken together our results provide a novel approach to analyzing learning with Bethe approximations and highlight when it can be expected to work or fail. |
| 关 键 词: | 图形模型; Bethe近似; 分区函数 |
| 课程来源: | 视频讲座网 |
| 最后编审: | 2019-09-08：lxf |
| 阅读次数: | 83 |