局部化支持向量机的定量鲁棒性
Quantitative Robustness of Localized Support Vector Machines
摘要:
如今,大量的可用数据对于基于内核的机器学习算法(如SVM)在运行时间和存储容量方面是一个挑战。地方办法可能有助于缓解这些问题,提高统计准确性。已经表明,这些地方性办法基本上是一致的和强有力的。这篇文章细化了对所谓的影响函数的鲁棒性分析,该函数表示学习方法的可微性:我们证明了我们的局部学习预测器对底层分布的可微依赖性。证明定理的假设可以在不知道任何关于这个分布的情况下得到验证。从应用的角度来看,这使得结果也很有趣。
英文摘要:
The huge amount of available data nowadays is a challenge for kernel-based machine learning algorithms like SVMs with respect to runtime and storage capacities. Local approaches might help to relieve these issues and to improve statistical accuracy. It has already been shown that these local approaches are consistent and robust in a basic sense. This article refines the analysis of robustness properties towards the so-called influence function which expresses the differentiability of the learning method: We show that there is a differentiable dependency of our locally learned predictor on the underlying distribution. The assumptions of the proven theorems can be verified without knowing anything about this distribution. This makes the results interesting also from an applied point of view.
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。