图 书 馆
更多数据更少工作：运行时作为单调减少数据集大小的功能More Data Less Work: Runtime As A Monotonically Decreasing Function of Data Set Size |
|
| 课程网址: | http://videolectures.net/mlss09us_srebro_mdlwrmdfdss/ |
| 主讲教师: | Nathan Srebro |
| 开课单位: | 芝加哥丰田技术学院 |
| 开课时间: | 2009-07-30 |
| 课程语种: | 英语 |
| 中文简介: |  |
| 课程简介: | We are used to studying runtime as an increasing function of the data set size, and are happy when this increase is not so bad (e.g. when the runtime increases linearly, or even polynomiall, with the data set size). Traditional runtime analysis of learning is also viewed this way, and studies how training runtime increases as more data is available. However, considering the true objective of training, which is to obtain a good predictor, I will argue that training runtime should actually be studied as a *decreasing* function of training set size. Focusing on training Support Vector Machines (SVMs) and combining ideas from optimization, statistical learning theory, and online methods. I will then present both theoretical and empirical results demonstrating how a simple stochastic subgradient descent approach indeed displays such monotonic decreasing behavior. I will also discuss a similar phenomena in the context of Gaussian mixture clustering, where it appears that excess data turns the problem from computationally intractable to computationally tractable. Joint work with Shai Shalev-Shwartz, Karthik Sridharan, Yoram Singer, Greg Shakhnarovich and Sam Roweis. |
| 关 键 词: | 数据集; 递增函数; 随机次梯度下降方法 |
| 课程来源: | 芝加哥丰田技术学院 |
| 最后编审: | 2019-08-09：cjy |
| 阅读次数: | 72 |