图 书 馆
目标风险的被动学习Passive Learning with Target Risk |
|
| 课程网址: | http://videolectures.net/colt2013_mahdavi_risk/ |
| 主讲教师: | Mehrdad Mahdavi |
| 开课单位: | 密歇根大学 |
| 开课时间: | 2013-08-09 |
| 课程语种: | 英语 |
| 中文简介: |  在本文中，我们考虑在被动设置中学习，但稍作修改。我们假设目标预期损失（也称为目标风险）是作为先验知识提前为学习者提供的。与大多数学习理论中仅将先验知识纳入泛化界限的研究不同，我们能够在学习过程中明确地利用目标风险。我们的分析揭示了学习样本复杂性的惊人结果：通过利用学习算法中的目标风险，我们证明当损失函数既强凸又平滑时，样本复杂度降低到O（log（1ε）），用于具有强凸损失函数的学习的样本复杂度O（1ε）的指数改善。此外，我们的证明是建设性的，并且基于这种设置的计算有效的随机优化算法，证明了所提出的算法实际上是有用的。 |
| 课程简介: | In this paper we consider learning in passive setting but with a slight modification. We assume that the target expected loss, also referred to as target risk, is provided in advance for learner as prior knowledge. Unlike most studies in the learning theory that only incorporate the prior knowledge into the generalization bounds, we are able to explicitly utilize the target risk in the learning process. Our analysis reveals a surprising result on the sample complexity of learning: by exploiting the target risk in the learning algorithm, we show that when the loss function is both strongly convex and smooth, the sample complexity reduces to O(log(1ϵ)), an exponential improvement compared to the sample complexity O(1ϵ) for learning with strongly convex loss functions. Furthermore, our proof is constructive and is based on a computationally efficient stochastic optimization algorithm for such settings which demonstrate that the proposed algorithm is practically useful. |
| 关 键 词: | 目标风险; 目标风险; 随机优化算法 |
| 课程来源: | 视频讲座网 |
| 最后编审: | 2019-03-13：chenxin |
| 阅读次数: | 85 |