论文标题
Torchntk：用于计算Pytorch模型神经切线内核的库
TorchNTK: A Library for Calculation of Neural Tangent Kernels of PyTorch Models
论文作者
论文摘要
我们介绍了Python库Torchntk，以计算Pytorch框架中神经网络模型的经验神经切线核（NTK）。我们提供了一种计算多层感知器的NTK的有效方法。我们将显式差异化实现与自动分化实现进行了比较，该实现的好处是将库的效用扩展到Pytorch支持的任何体系结构，例如卷积网络。库的一个功能是，我们将用户曝光到layerwise ntk组件，并表明在某些方案中，layerwise计算更有效。我们进行初步实验，以证明软件的用例并探测NTK。
We introduce torchNTK, a python library to calculate the empirical neural tangent kernel (NTK) of neural network models in the PyTorch framework. We provide an efficient method to calculate the NTK of multilayer perceptrons. We compare the explicit differentiation implementation against autodifferentiation implementations, which have the benefit of extending the utility of the library to any architecture supported by PyTorch, such as convolutional networks. A feature of the library is that we expose the user to layerwise NTK components, and show that in some regimes a layerwise calculation is more memory efficient. We conduct preliminary experiments to demonstrate use cases for the software and probe the NTK.
