arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1802.04350cs.LGstat.ML
收藏

基于代价感知学习的多实验可辨识性改进

Cost-Aware Learning for Improved Identifiability with Multiple Experiments

Purdue University(普渡大学)

Longyun Guo, Jean Honorio, John Morgan

摘要:

我们分析了从多个实验中学习的样本复杂性,其中实验者有一个总预算来获得样本。在这个问题中,学习者应该选择一个在多个实验及其相关数据分布方面表现良好的假设。每个收集的样本都与取决于特定实验的成本相关联。在我们的设置中,学习者执行$m$实验,同时产生总成本$C$。我们首先表明,从多个实验中学习可以提高可识别性。此外,通过使用Rademacher复杂性方法,我们证明了训练和泛化误差之间的差距是$O(C^{-1/2})$。我们也提供了一些例子,线性预测,两层神经网络和核方法。

英文摘要:

We analyze the sample complexity of learning from multiple experiments where the experimenter has a total budget for obtaining samples. In this problem, the learner should choose a hypothesis that performs well with respect to multiple experiments, and their related data distributions. Each collected sample is associated with a cost which depends on the particular experiments. In our setup, a learner performs $m$ experiments, while incurring a total cost $C$. We first show that learning from multiple experiments allows to improve identifiability. Additionally, by using a Rademacher complexity approach, we show that the gap between the training and generalization error is $O(C^{-1/2})$. We also provide some examples for linear prediction, two-layer neural networks and kernel methods.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑