图 书 馆
改变环境的有效学习算法Efficient Learning Algorithms for Changing Environments |
|
| 课程网址: | http://videolectures.net/icml09_seshadhri_elafc/ |
| 主讲教师: | Comandur Seshadhri |
| 开课单位: | 剑桥大学 |
| 开课时间: | 2009-08-26 |
| 课程语种: | 英语 |
| 中文简介: |  我们在一个不经意的变化环境中学习在线学习。后悔的标准衡量标准限制了在线学习者的成本与后见之明的最佳决策之间的差异。因此，后悔最小化算法往往会收敛到静态最佳最优，显然是在不断变化的环境中的次优行为。另一方面，为加强遗憾和允许更多动态算法而提出的各种度量标准会产生效率低下的算法。我们提出了一个不同的性能指标，它加强了后悔的标准度量，并衡量了不断变化的比较器的性能。然后，我们描述了一系列基于数据流的约简，这些算法将最小化（标准）遗憾的算法转换为自适应算法，尽管只产生多对数计算开销。利用这种减少，我们获得了有效的低自适应遗憾算法，用于在线凸优化问题。这可以应用于各种学习场景，即在线投资组合选择，我们描述了实验结果，显示了适应性的优势。 |
| 课程简介: | We study online learning in an oblivious changing environment. The standard measure of regret bounds the difference between the cost of the online learner and the best decision in hindsight. Hence, regret minimizing algorithms tend to converge to the static best optimum, clearly a suboptimal behavior in changing environments. On the other hand, various metrics proposed to strengthen regret and allow for more dynamic algorithms produce inefficient algorithms. We propose a different performance metric which strengthens the standard metric of regret and measures performance with respect to a changing comparator. We then describe a series of data-streaming-based reductions which transform algorithms for minimizing (standard) regret into adaptive algorithms albeit incurring only poly-logarithmic computational overhead. Using this reduction, we obtain efficient low adaptive-regret algorithms for the problem of online convex optimization. This can be applied to various learning scenarios, i.e. online portfolio selection, for which we describe experimental results showing the advantage of adaptivity. |
| 关 键 词: | 在线学习; 后悔最小化算法; 自适应算法 |
| 课程来源: | 视频讲座网 |
| 最后编审: | 2019-04-24：lxf |
| 阅读次数: | 74 |