A Overview

C.1 More details on datasets and models being explained For text datasets, We employ three-layer convolutional neural networks. Due to the large number of parameters in the target model (over 1.6 million), we do not implement Surrogate derivative: We first transform Eqn. We then follow Y eh et al. T arget derivative: We directly adopt Eqn. ( t 1) ( t 1) For last layer embeddings and neural tangent kernels, we directly use Eqn. We train 5 models simultaneously on a single GPU for speed up.