BriefGPT.xyz
Oct, 2020
核感知机的教学维度
The Teaching Dimension of Kernel Perceptron
HTML
PDF
Akash Kumar, Hanqi Zhang, Adish Singla, Yuxin Chen
TL;DR
本文研究了算法机器教学问题，针对核化感知器的不同特征映射家族建立了教学复杂度，即教学维度和样本复杂度。在特定的数据分布平滑假设下，建立了关于近似教学Gaussian内核感知器的复杂度严格边界，并在线性，多项式和高斯核感知器的几个典型场景下提供了最佳（近似）教学集的数值示例。
Abstract
algorithmic machine teaching
has been studied under the linear setting where exact teaching is possible. However, little is known for teaching nonlinear learners. Here, we establish the
sample complexity
of teach
→