图 书 馆
超越随机梯度下降Beyond Stochastic Gradient Descent |
|
| 课程网址: | http://videolectures.net/roks2013_bach_optimization/ |
| 主讲教师: | Francis R. Bach |
| 开课单位: | INRIA-SIERRA项目团队 |
| 开课时间: | 2013-08-26 |
| 课程语种: | 英语 |
| 中文简介: |  |
| 课程简介: | Many machine learning and signal processing problems are traditionally cast as convex optimization problems. A common difficulty in solving these problems is the size of the data, where there are many observations ("large n") and each of these is large ("large p"). In this setting, online algorithms which pass over the data only once, are usually preferred over batch algorithms, which require multiple passes over the data. In this talk, I will present several recent results, showing that in the ideal in finite-data setting, online learning algorithms based on stochastic approximation should be preferred, but that in the practical finite-data setting, an appropriate combination of batch and online algorithms leads to unexpected behaviors, such as a linear convergence rate with an iteration cost similar to stochastic gradient descent. (joint work with Nicolas Le Roux, Eric Moulines and Mark Schmidt) |
| 关 键 词: | 随机梯度; 数据算法; 迭代成本 |
| 课程来源: | 视频讲座网 |
| 数据采集: | 2023-04-22：chenxin01 |
| 最后编审: | 2023-05-18：chenxin01 |
| 阅读次数: | 11 |