图 书 馆
随机PCA算法与遗憾的界限，在尺寸的对数Randomized PCA Algorithms with Regret Bounds that are Logarithmic in the Dimension |
|
| 课程网址: | http://videolectures.net/mlss06tw_warmuth_rparb/ |
| 主讲教师: | Manfred K. Warmuth |
| 开课单位: | 加州大学 |
| 开课时间: | 2007-02-25 |
| 课程语种: | 英语 |
| 中文简介: |  |
| 课程简介: | We design an on-line algorithm for Principal Component Analysis. The instances are projected into a probabilistically chosen low dimensional subspace. The total expected quadratic approximation error equals the total quadratic approximation error of the best subspace chosen in hindsight plus some additional term that grows linearly in dimension of the subspace but logarithmically in the dimension of the instances. |
| 关 键 词: | 主成分分析的线算法; 低维子空间; 子空间维数 |
| 课程来源: | 视频讲座网 |
| 最后编审: | 2020-06-15：wuyq |
| 阅读次数: | 86 |