Gradient Kernel Regression
Not on the map. Why?
Abstract (arXiv)
In this article a surprising result is demonstrated using the neural tangent kernel. This kernel is defined as the inner product of the vector of the gradient of an underlying model evaluated at training points. This kernel is used to perform kernel regression. The surprising thing is that the accuracy of that regression is independent of the accuracy of the underlying network.
Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 6 of its 9 references that are in the map. First posted on arXiv 13 Apr 2021.
Builds on
6 of 9 references.
References · 6
- 2015Deep Residual Learning for Image Recognitioncited by 51,809
- 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
- 2018Neural Tangent Kernel: Convergence and Generalization in Neural Networkscited by 2,597
- 2017Deep Image Priorcited by 1,097
- 2020Every Model Learned by Gradient Descent Is Approximately a Kernel Machinecited by 53
- 2016A Powerful Generative Model Using Random Weights for the Deep Image Representationcited by 14
Built on by
Not cited yet.