论文标题
通过括号进行预算学习
Budget Learning via Bracketing
论文作者
论文摘要
移动/物联网中的常规机器学习应用程序将数据设置为云服务器以进行预测。由于成本考虑（功率，延迟，货币），因此希望最大程度地减少设备与服务器的变速器。预算学习（BL）问题构成了学习者的目标，因为它最大程度地减少了云的使用，同时却没有明显的准确性损失，这是在限制的限制下，即使用的方法是可以实现的。 我们通过括号的概念为BL问题提出了一种新的公式。具体而言，我们建议将“简单”类的$ h^ - ，h^+$夹心，$ g，$ $ g，$ $ h^+$，以便几乎总是总是总是如此。在实例上，如果$ x $，如果$ h^+（x）= h^ - （x）$，我们利用本地处理，并绕过云。我们探讨了这种表述的理论方面，提供了Pac风格的可学习性定义；将预算可学习性的概念与通过括号的近似性相关联；并对其性质进行VC理论分析。我们从经验上验证了现实世界数据集的理论，证明了基于门控的方法的性能提高了。
Conventional machine learning applications in the mobile/IoT setting transmit data to a cloud-server for predictions. Due to cost considerations (power, latency, monetary), it is desirable to minimise device-to-server transmissions. The budget learning (BL) problem poses the learner's goal as minimising use of the cloud while suffering no discernible loss in accuracy, under the constraint that the methods employed be edge-implementable. We propose a new formulation for the BL problem via the concept of bracketings. Concretely, we propose to sandwich the cloud's prediction, $g,$ via functions $h^-, h^+$ from a `simple' class so that $h^- \le g \le h^+$ nearly always. On an instance $x$, if $h^+(x)=h^-(x)$, we leverage local processing, and bypass the cloud. We explore theoretical aspects of this formulation, providing PAC-style learnability definitions; associating the notion of budget learnability to approximability via brackets; and giving VC-theoretic analyses of their properties. We empirically validate our theory on real-world datasets, demonstrating improved performance over prior gating based methods.
