发帖
雷达卡
On the Power of Localized Perceptron for Label-Optimal Learning of
Halfspaces with Adversarial Noise
Jie Shen 1
Abstract the learner must pay for each label it wishes to be revealed.
We study online active learning of homogeneous The goal is to design querying strategies to avoid less infor-
halfspaces in Rd with adversarial noise where mative labeling requests, e.g. the labels that can be inferred
...
京公网安备 11010802022788号
